title,venue,link,paper type,gender variable?,gender variable usage,quote,primary referent,multiple referents?,gender categories,non-binary?,gender determination,goal,bias/fairness?,notes,flag for review?
Break the Loop: Gender Imbalance in Music Recommenders,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446033,short,yes,,,provider,no,male / female,no,self-identification,audit system behavior,yes,,
Predicting User Demography and Device from News Comments,SIGIR21,https://dl.acm.org/doi/pdf/10.1145/3404835.3463024,short,yes,,,users,yes,male / female,no,self-identification,gender prediction,no,,
Do Neural Ranking Models Intensify Gender Bias?,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401280,short,yes,,,subject,no,male / female / non-gendered,extended,annotators,audit system behavior,yes,, 
Reputation (In)dependence in Ranking Systems: Demographics Influence Over Output Disparities,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401278,short,yes,,,users,no,male / female,ack,self-identification,audit system behavior,yes,mitigation to ensure that users' reputation in ranking systems is independent of sensitive attributes,
"How to Evaluate Humorous Response Generation, Seriously?",CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176879,short,yes,,,users,no,male / female,no,self-identification,user study or survey,no,Results show that demographics and joke topics can partly explain variation in humor judgments. We expect that these insights will aid humor evaluation and interpretation. The findings can also be of interest for humor generation methods in conversational systems.,
Investigating User Perception of Gender Bias in Image Search: The Role of Sexism,SIGIR18,https://dl.acm.org/doi/pdf/10.1145/3209978.3210094?accessTab=true,short,yes,,,users,yes,male / female,no,self-identification / annotators,user study or survey,yes,"However, to date, little is known concerning how users perceive bias in search results, and the degree to which their perceptions differ and/or might be predicted based on user attributes. One particular area of search that has recently gained attention, and forms the focus of this study, is image retrieval and gender bias.",
Decoding the Style and Bias of Song Lyrics,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331363,short,yes,,,subject,no,male / female,no,annotators,user study or survey,yes,The central idea of this paper is to gain a deeper understanding of song lyrics computationally. This correlation indicates that song lyrics reflect the biases that exist in society. Increasing consumption of music and the effect of lyrics on human emotions makes this analysis important.,
Skip or Stay: Users' Behavior in Dealing with Onsite Information Interaction Crowd-Bias,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022160,short,yes,,,users,no,male / female,no,self-identification,user study or survey / gender personalization,no,"Our general aim is to improve our understanding of onsite users’ behavior, which allow us to create better online and onsite contextual suggestion systems. We focus on the cultural heritage domain and have collected onsite users’ information interaction logs of visits in a museum. This prompts the question: How to understand users’ behavior in order to be able to predict their onsite behaviors?",
On the Orthogonality of Bias and Utility in Ad hoc Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463110,short,yes,,,subject,no,male / female,no,annotators,audit system behavior,yes,,
Design Issues in Automatically Generated Persona Profiles: A Qualitative Analysis from 38 Think-Aloud Transcripts,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298942,short,yes,,,subject,yes,male / female,no,self-identification,persona generation / user study or survey,no,synthetic?,
On the Privacy of Federated Pipelines,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462996,short,yes,,,subject,no,male / female,no,self-identification,protect gender variable,yes,,
Morphologically Annotated Amharic Text Corpora,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463237,short,yes,,,subject,no,male / female,no,annotators,linguistic gender,no,,
Read what you need: Controllable Aspect-based Opinion Summarization of Tourist Reviews,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401269,short,yes,,,provider,no,male / female,no,inferred,gender diversity & inclusion (user controlled),yes,inferred from name,
An Analysis of Query Reformulation Techniques for Precision Medicine,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331289,short,yes,,,provider,no,male / female,no,self-identification,indexing clinical trials,no,,
Fair Classification with Counterfactual Learning,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401291,short,yes,,,users,no,male / female,no,self-identification,audit system behavior,yes,"In this paper, we design a counterfactual framework to model fairness-aware learning which benefits from counterfactual reasoning to achieve more fair decision support systems. ",
Surveying User Reactions to Recommendations Based on Inferences Made by Face Detection Technology,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109875,short,yes,,,users,no,male / female,no,inferred,audit system behavior / user study or survey,yes,inferred from face,
Find my next job: labor market recommendations using administrative big data,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346992,short,yes,,,users,no,male / female,no,self-identification,audit system behavior,yes,,
Attribute-based evaluation for recommender systems: incorporating user and item attributes in evaluation metrics,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347049,short,yes,,,users,no,male / female,no,self-identification,audit system behavior,no,,
"User preferences in recommendation algorithms: the influence of user diversity, trust, and product category on privacy perceptions in recommender algorithms",RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240393,short,yes,,,users,yes,male / female,no,self-identification,user study or survey,no,,
Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412220,short,yes,,,users,no,male / female,no,self-identification,gender personalization,yes,,
A Novel Recommender System for Helping Marathoners to Achieve a New Personal-Best,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109874,short,yes,,,users,no,male / female,no,self-identification,gender personalization,no,,
The Effect of Gender and Age on the Factors That Influence Healthy Shopping Habits in E-Commerce,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209253,short,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,no,"The result of our analysis suggests that social support, relative price and perceived product quality significantly influence healthy shopping habits in e-commerce shoppers. In addition, females are more influenced by social support to adopt healthy shopping habits compared to male eshoppers. ",
"How Relevance Feedback is Framed Affects User Experience, but not Behaviour",CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298957,short,no,tag,"""For example, when presented with documents retrieved using the query ""gender recognition"", participants were asked to mark documents related to ""face recognition"".",,,,,,,,,
Online Job Search: Study of Users' Search Behavior using Search Engine Query Logs,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210125,short,no,user attribute / profile,"""This may indicate that, users prefer to continue their job searches through vertical search engines that may provide better job search services for them, such as constraint for cities, sex, age, or salary.""",,,,,,,,,
Influence Function for Unbiased Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401321,short,no,contextualize argument,"""... recommender systems are always subject to variety of biases, such as selection bias, position bias, gender bias, popularity bias.""",,,,,,,,,
Needs for Relatedness: LGBTQ+ Individuals' Information Seeking and Sharing in an Online Community,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446040,short,no,user attribute / profile,"""... there might also be unique characteristics of the online information behavior of each sexual and gender minority group.""",,,,,,,,,
The Influence of Device Type on Querying Behavior and Learning Outcomes in a Searching as Learning Task with a Laptop or Smartphone,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378000,short,no,demographic data,"""To control for gender, age, and educational level, participants were paired based on those attributes.""",,,,,,,,,
Linguistic Design of In-Vehicle Prompts in Adaptive Dialog Systems: An Analysis of Potential Factors Involved in the Perception of Naturalness,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320469,short,no,gender distribution,"""... and a gender distribution of... """,,,,,,,,,
Towards Identifying User Intentions in Exploratory Search using Gaze and Pupil Tracking,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022131,short,no,demographic data,"""The experimental procedure started with the collection of the users' age, sex, and profession.""",,,,,,,,,
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Models,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394880,short,no,demographic data,"""We inquired on the user's gender, age, BMI... """,,,,,,,,,
The Role of Trust in Personal Data Sharing in the Context of e-Assessment and the Moderating Effect of Special Educational Needs,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394876,short,no,demographic data,"""... and demographic characteristics (sex, age, educational level, SEND).""",,,,,,,,,
A Structural Equation Model of Information Retrieval Skills,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022142,short,no,contextualize argument,"""... they conducted analysis to determine which of the following factors contribute to the level of people's Internet skills: gender, age, educational attainment, Internet experience, and the amount of time spent on the Internet.""",,,,,,,,,
Neural Representations in Hybrid Recommender Systems: Prediction versus Regularization,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463051,short,no,user attribute / profile,"""Side information of the users and items include the content of items (e.g., category, title, description) and profile of users (e.g., age, location, gender), respectively.""",,,,,,,,,
Comparing Academic and Everyday-Life Information Seeking Behavior Among Millennial Students,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378006,short,no,gender distribution,"""The survey sample included 67.2% women (n=2396), 31.7% men (n=1129), and 1.1% (n=38) who self-identified their gender.""",,,,,,,,,
Understanding Music Listening Intents During Daily Activities with Implications for Contextual Music Recommendation,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176885,short,no,gender distribution,"""(caption of figure) Age and Gender distribution among respondents""",,,,,,,,,
Exploring Multi-List User Interfaces for Similar-Item Recommendations,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456809,short,no,gender distribution,"""Gender distribution among participants... """,,,,,,,,,
Strangers in a Strange Land: A Study of Second Language Speakers Searching for e-Services,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022133,short,no,demographic data,"""Each session followed the same process of each participant filling in a demographic questionnaire which collected information on their area of study; age; gender; nationality... """,,,,,,,,,
Revealing the Role of User Moods in Struggling Search Tasks,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331353,short,no,demographic data,"""Workers willing to particpiate were first asked to respond to a few general questions pertaining to their gender, age and select a mood that could describe their state... """,,,,,,,,,
Personification of the Amazon Alexa: BFF or a Mindless Companion,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176868,short,no,contextualize argument,mentioned in related work,,,,,,,,,
A Cross-Platform Collection for Contextual Suggestion,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080752,short,no,demographic data,"""Moreoever, user's age and gender are optionally included.""",,,,,,,,,
Automatic Summarization of Domain-specific Forum Threads: Collecting Reference Data,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022127,short,no,demographic data,"""The users provided some basic information on the login screen, such as their gender and age.""",,,,,,,,,
Evaluation of the Comprehensiveness of Bar Charts with and without Stacking Functionality using Eye-Tracking,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022147,short,no,demographic data,"""In addition, the participants provided information about their age, job, gender, corrective lenses or glasses, and some general feedback.""",,,,,,,,,
Transparent Tree Ensembles,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210151,short,no,demographic data,used in table,,,,,,,,In this work we present a method for deriving explanations for instance-level decisions in tree ensembles.,
Translating Representations of Knowledge Graphs with Neighbors,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210085,short,no,contextualize argument,"""For example, when predicting whether two students are classmates or not, it is more useful to know the schools they study at than knowing their gender or nationality.""",,,,,,,,,
On Anonymous Commenting: A Greedy Approach to Balance Utilization and Anonymity for Instagram Users,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331364,short,no,future work / footnote / citations,"""Further research can be conducted concerning analytics on location, gender and age of the commenters or temporality of the comments.",,,,,,,,,
Multi-grouping Robust Fair Ranking,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401292,short,no,future work / footnote / citations,footnote,,,,,,,,,
Personality Dimensions of Intelligent Personal Assistants,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377993,short,no,future work / footnote / citations,"""The next phase of our study aims to test user preferences for warm-competent response, and examine the dependence of these preferences in conversational context and current tasks... user characteristics... and IPA vocal characteristics (gender, speed, use of pronouns).""",,,,,,,,,
Generating Clinical Queries from Patient Narratives: A Comparison between Machines and Humans,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080661,short,no,future work / footnote / citations,"""Particular points of inquiry would be in the evaluation of medical specific features, such as mentions of particulare diseases affecting the patient, permanent demographic information (age, gender) and negated contents (e.g. ""no fever"").""",,,,,,,,,
Investigating the Interplay Between Searchers' Privacy Concerns and Their Search Behavior,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331280,short,no,demographic data,"""Demographic information was collected first (including age, gender and educational information).""",,,,,,,,,
When Choice Happens: A Systematic Examination of Mouse Movement Length for Decision Making in Web Search,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463055,short,no,future work / footnote / citations,"""It has been shown that mouse movements can disclose sensible demographics information such as gender and age, which could be exploited... """,,,,,,,,,
Improving Neural Text Style Transfer by Introducing Loss Function Sequentiality,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463026,short,no,future work / footnote / citations,"""Future work implies the replication of this study over different transfer tasks such as gender, formality or offensiveness... """,,,,,,,,,
A Neural Language Model for Query Auto-Completion,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080758,short,no,future work / footnote / citations,"""Our neural language model can be easily adapted to personalized QAC by remembering a specific user's query session state or a specific gender's general state.""",,,,,,,,,
Personalized Entity Search by Sparse and Scrutable User Profiles,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378011,short,no,user attribute / profile,"""It captures demographic attributes (age, gender, location etc.)... """,,,,,,,,,
An Analysis of Information Types and Cognitive Activities Involved in Cross-session Search,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446044,short,no,demographic data,"""... demographic information (i.e., age, gender, education background)... """,,,,,,,,,
On Cultural-centered Graphical Passwords: Leveraging on Users' Cultural Experiences for Improving Password Memorability,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209254,short,no,user attribute / profile,"""Furthermore, user choices are influenced by human attributes in an image (e.g., race, age, gender)... """,,,,,,,,,
Personality and Engagement with Digital Mental Health Interventions,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456823,short,no,demographic data,"""... demographic questions (age range, gender)... """,,,,,,,,,
Inferring Cognitive Style from Eye Gaze Behavior During Information Visualization Usage,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394881,short,no,demographic data,"""... demographic quiestionnaire, which included age, gender... """,,,,,,,,,
Cogito ergo quid? The Effect of Cognitive Style in a Transparent Mobile Music Recommender System,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394871,short,no,demographic data,"""... a quiestionnaire... including age, gender... """,,,,,,,,,
More than Words: The Impact of Memory on How Undergraduates with Dyslexia Interact with Information,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378005,short,no,gender distribution,"""While we would have preferred a gender-balanced sample, no difference in challenges between males and remales with dyslexia has been identified in the literature.""",,,,,,,,,
Towards Differentially Private Text Representations,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401260,short,no,user attribute / profile,"""In NLP tasks, the input text often provides sufficient clues to portray the authors, such as their genders, ages, and other important attributes.""",,,,,,,,,
Detecting Persuasive Arguments based on Author-Reader Personality Traits and their Interaction,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320467,short,no,contextualize argument,mentioned in related work,,,,,,,,,
Rating-based Preference Elicitation for Recommendation of Stress Intervention,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3324990,short,no,future work / footnote / citations,footnote,,,,,,,,,
Investigating Serial Position Effects in Sequential Group Decision Making,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209255,short,no,future work / footnote / citations,mentioned in conclusion/future work,,,,,,,,,
Personality Correlates of Music Audio Preferences for Modelling Music Listeners,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394874,short,no,contextualize argument,mentioned in related work,,,,,,,,,
Does BERT Pay Attention to Cyberbullying?,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463029,short,no,tag,"""Twitter-sexism"" dataset: Twitter message conaining tweets labelled as sexist or not",,,,,,,,,
Information Sharing and Search Collaboration Activities of Health Consumers in South East Asia,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022125,short,no,future work / footnote / citations,"""As well as cultural and gender roles that influence health searching.""",,,,,,,,,
CitySearcher: A City Search Engine For Interests,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080742,short,no,demographic data,"""Moreover, for relevance assessment, we collected 800 ratings... both genders, age 18-60... """,,,,,,,,,
Personality Bias of Music Recommendation Algorithms,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412223,short,no,contextualize argument,"personality bias, quotes Michael",,,,,,,,,
Deep inventory time translation to improve recommendations for real-world retail,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240380,short,no,user attribute / profile,used in diagram,,,,,,,,,
A Cross-Cultural Analysis of Trust in Recommender Systems,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209251,short,no,gender distribution,"""Across the countries, we observed a comparable distribution of subjects in terms of gender, age, and IT literacy.""",,,,,,,,,
Predicting Users' Personality from Instagram Pictures: Using Visual and/or Content Features?,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209248,short,no,gender distribution,"""Age and gender information indicated adequate distribution.""",,,,,,,,,
How Do User Opinions Influence Their Interaction With Web Search Results?,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456824,short,no,demographic data,"""... a few general background questions regarding age, gender... """,,,,,,,,,
ClusterExplorer: Enable User Control over Related Recommendations via Collaborative Filtering and Clustering,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412221,short,no,demographic data,"""The welcome survey. inquired basic information, such as how often the user reads books, age and gender.""",,,,,,,,,
PyRecGym: a reinforcement learning gym for recommender systems,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346981,short,no,user attribute / profile,"""... the user profile, which contains detailed information about users (e.g., gender, age)... """,,,,,,,,,
Investigating Listeners’ Responses to Divergent Recommendations,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3418482,short,no,user attribute / profile,"""... including: age, gender, auditacity, currency... """,,,,,,,,,
A hierarchical bayesian model for size recommendation in fashion,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240388,short,no,tag,"""... the gender of the article and the size system... """,,,,,,,,,
An Insurance Recommendation System Using Bayesian Networks,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109907,short,no,demographic data,"""... customer demographics (age, gender, marital status, etc.)... """,,,,,,,,,
Quick and accurate attack detection in recommender systems through user attributes,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347050,short,no,user attribute / profile,"""The user attributes that are included in this study are age, occupation and gender.""",,,,,,,,,
Dataset of Natural Language Queries for E-Commerce,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446043,short,no,demographic data,"""... the participants answered questions about their demographics background: (1) their age, (2) their gender, and (3) their self-assessed domain knowledge... """,,,,,,,,,
User-centered evaluation of strategies for recommending sequences of points of interest to groups,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346988,short,no,gender distribution,"""... 50.8% were females and 48.3 were males. One participant preferred to not specify the gender.""",,,,,,,,,
Interpretable Contextual Team-aware Item Recommendation: Application in Multiplayer Online Battle Arena Games,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412211,short,no,gender distribution,"""25% female, 68% male and one subject did not disclose the gender.""",,,,,,,,,
Baby Shark to Barracuda: Analyzing Children’s Music Listening Behavior,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3478856,short,no,contextualize argument,"""Psychological research has also investigated music listening behavior among children of different age groups based on factors such as gender, location, and education level.""",,,,,,,,,
Personalized Response Generation via Domain adaptation,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080706,short,applied,vectorized / grouped,"""... we explicitly calculate the user vector u for each user based on the user-specific information (e.g., identity, age, gender, personal information)...""",,,,,,,,,
Factuality Checking in News Headlines with Eye Tracking,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401221,short,applied,user attribute / profile,"""For the categorical variables of position (middle, bottom), gender (male), and factuality (true), there are k - 1 fewer factors than number of categories (k).""",,,,,,,,,
Metadata Matters in User Engagement Prediction,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401201,short,applied,vectorized / grouped,"""... the three basic features, including the user gender, webpage url and the local time have been converted to three k(=8) dimensional dense vectors...""",,,,,,,,,
Towards Explainable Retrieval Models for Precision Medicine Literature Search,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401277,short,applied,tag,"""For the Demographic classifier, we first detect whether a document mentions gender or age information, then check whether the information matches that in the query.""",,,,,,,,Applied but “parse document” happens after the inference,
Learning Discriminative Joint Embeddings for Efficient Face and Voice Association,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401302,short,applied,demographic data,"""That is, the final outputs of the proposed network model not only can preserve much information about the gender, nationality and age, but also contain valuable information for identity analysis.""",,,,,,,,,
Predicting Session Length in Media Streaming,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080695,short,applied,user attribute / profile,"""Some features, which we call ""user-based"" are features that we assume do not change between sessions, for example the gender of the user.""",,,,,,,,,
SAIN: Self-Attentive Integration Network for Recommendation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331342,short,applied,user attribute / profile,"""Other than user-item interactions, we leveraged features such as age and gender for users and genres for movies.""",,,,,,,,,
Predicting Session Length for Product Search on E-commerce Platform,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401219,short,applied,user attribute / profile,"""User features consist of the user's anonymized unique account number... user's age and gender (if self-reported, taken as-is, otherwise derived from the behavior data using a production system, discussion of which is out of scope).""",,,,,,,,,
An Information Retrieval Framework for Contextual Suggestion Based on Heterogeneous Information Network Embeddings,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210103,short,applied,user attribute / profile,"""The input to the system is a list of requests (R) and user profiles (U), where user profiles are a list of rated attractions (preferences), gender and age.""",,,,,,,,,
Detecting Concept Drift In Medical Triage,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401228,short,applied,tag,"""We parse the document eaders to extract structured fields like gender and age, and encode the report body as a bag of words.""",,,,,,,,,
Personalized fairness-aware re-ranking for microlending,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347016,short,applied,user attribute / profile,"""... the corresponding categorical protected attribute, such as religion, race, or gender.""",,,,,,,,,
Psychographic Matching between a Call Center Agent and a Customer,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456815,short,applied,user attribute / profile,"""The variables of the function are the attributes of Ag and Cu (Att: gender, age... """,,,,,,,,,
Chatty Goose: A Python Framework for Conversational Search,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462782,short,N/A,,"""How do sexual and asexual reproduction affect [Darwin's theory]?""",,,,,,,,,
A Pairwise Probe for Understanding BERT Fine-Tuning on Machine Reading Comprehension,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401195,short,N/A,,"""When does the movie battle of the sexes come out?""",,,,,,,,,
Summary and Prejudice: Online Reading Preferences of Users with Intellectual Disability,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446039,short,N/A,,"""They require information on serious issues like sexual health and cancer as these can affect their daily lives.""",,,,,,,,,
Predicting Zika Prevention Techniques Discussed on Twitter: An Exploratory Study,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176874,short,N/A,,"""Prevention of Sexually Transmitted Zika Virus Infection""",,,,,,,,,
Exploring the Power of Visual Features for the Recommendation of Movies,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320470,short,N/A,,"""interrupted sex"" as a keyword",,,,,,,,,
Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers,SIGIR21,https://dl.acm.org/doi/pdf/10.1145/3404835.3462949?accessTab=true,full,yes,,,subject,no,male / female,ack,annotators,audit system behavior ,yes,mitigate bias in existing framework by introducing new framework,
Exploring User-Specific Information in Music Retrieval,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080772,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,,
When Fair Ranking Meets Uncertain Inference,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462850,full,yes,,,subject,no,male / female,ack,inferred,audit system behavior,yes,"Our results suggest that developers should not use inferred demographic data as input to fair ranking algorithms, unless the inferences are extremely accurate. Inferred from name",
"My Mouse, My Rules: Privacy Issues of Behavioral User Profiling via Mouse Tracking",CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446011,full,yes,,,users,no,male / female / none,extended,self-identification,audit system behavior / protect gender variable,yes,,
Towards Personalized Fairness based on Causal Notion,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462966,full,yes,,,users,no,male / female,no,self-identification,audit system behavior,yes,,
Effect of Values and Technology Use on Exercise: Implications for Personalized Behavior Change Interventions,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320451,full,yes,,,users,no,male / female,no,self-identification,user study or survey / gender personalization,no,"This study is a unique view of the interaction between technology use, demographics, and value systems of a representative US population sample, allowing for rich user modeling in the aims of promoting exercise.",
Modeling Improvement for Underrepresented Minorities in Online STEM Education,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320463,full,yes,,,users,no,male / female,no,self-identification,user study or survey,yes,"In this paper we investigate student success in an online learning space, comparing students from underrepresented groups to their peers in terms of online learning behaviors mined from log files. ",
Culture and Health Belief Model: Exploring the Determinants of Physical Activity Among Saudi Adults and the Moderating Effects of Age and Gender,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456826,full,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,no,"Finally, we discuss the implication of our findings and offer design guidelines for persuasive interventions that appeal to both a broad audience and tailored to a particular group depending on their gender and age group.",
Perceived Persuasive Effect of Behavior Model Design in Fitness Apps,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209240,full,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,no,"we conducted an empirical study among 669 participants to uncover: (1) how the perceived persuasiveness of behavior model design influences three social cognitive theory (SCT) determinants of behavior: self-efficacy, self-regulation and outcome expectation; and (2) the moderating effect of gender-based personalization.",
Predict Demographic Information Using Word2vec on Spatial Trajectories,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209224,full,yes,,,users,no,male / female,no,self-identification,gender prediction,no,data is from Sherlock and CARS,
What Makes an Image Tagger Fair?,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320442,full,yes,,,users,yes,male / female,no,self-identification / annotators,user study or survey,yes,"We conduct an experiment to shed light on the factors influencing the perception of “fairness."" Participants are shown a photo along with two descriptions (human- and algorithm-generated). They are then asked to indicate which is “more fair"" in the context of a dating site, and explain their reasoning.",
PreSizE: Predicting Size in E-Commerce using Transformers,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462844,full,yes,,,subject,yes,male / female / unisex,extended,inferred / annotators,audit system behavior,no,inferred from purchase history,
Do Users Have Contextual Preferencesfor Smartphone Power Management?,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456813,full,yes,,,users,no,male / female / non-binary,extended,self-identification,user study or survey,no,"Participants rated their willingness to accept each tradeoff to save power. Contrasting current power-saving modes, we found that participants’ preferences did indeed vary by context.",
Fixation and Confusion: Investigating Eye-tracking Participants' Exposure to Information in Personas,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176391,full,yes,,,users,yes,male / female,no,self-identification,persona generation / user study or survey,no,"user confusion, synthetic?",
Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401101,full,yes,,,users,no,male / female / none,extended,self-identification,gender personalization,no,,
Understanding Ephemeral State of Relevance,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020176,full,yes,,,users,no,male / female,no,self-identification,user study or survey ,no,user judgements of search result relevance,
Hands-free but not Eyes-free: A Usability Evaluation of Siri while Driving,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377962,full,yes,,,users,no,male / female,no,self-identification,user study or survey,no,user evaluation of Siri,
"Learning From the News: The Role of Topic, Multimedia and Interest in Knowledge Retention",CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020166,full,yes,,,users,no,male / female,no,self-identification,user study or survey,no,Participants engaged with news stories and completed knowledge retention tests to evaluate their ability to remember the content.,
What Makes a Top-Performing Precision Medicine Search Engine? Tracing Main System Features in a Systematic Way,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401048,full,yes,,,provider,no,male / female,no,self-identification,indexing clinical trials,no,,
Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331254,full,yes,,,subject,no,male / female,no,annotators,gender personalization,no,,
A Personal Privacy Preserving Framework: I Let You Know Who Can See What,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3209995,full,yes,,,users,no,male / female,no,annotators,audit system behavior / protect gender variable / user study or survey,no,,
Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401144,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,"They are trying to do gender inference here with a joint model, Amazon and Movielens public dataset",
Would you Like to Talk about Sports Now?: Towards Contextual Topic Suggestion for Open-Domain Conversational Agents,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377974,full,yes,,,users,no,male / female,no,inferred,gender prediction,no,"""The conversation data were collected by participating in Amazon Alexa Prize 2018 competition [17].""",
Recommending Video Games to Adults with Autism Spectrum Disorder for Social-Skill Enhancement,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394867,full,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,no,We have developed a gaming and personalized recommender system that suggests therapeutic games to adults with ASD which can improve their social-interactive skills.,
Exploring author gender in book rating and recommendation,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240373,full,yes,,,provider,no,male / female,ack,annotators,audit system behavior,yes,,
The Impacts of Item Features and User Characteristics on Users' Perceived Serendipity of Recommendations,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394863,full,yes,,,users,no,male / female,no,self-identification,user study or survey,no,"In this paper, we have attempted to fill in this vacancy based on results of a large-scale user survey (involving over 10,000 users). We have analyzed the correlation between different types of features (i.e., numerical and categorical) with user perceptions, and furthermore identified the interaction effect from user characteristics (such as personality traits and curiosity). ",
Tracking and Modeling Subjective Well-Being Using Smartphone-Based Digital Phenotype,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394855,full,yes,,,users,no,male / female,no,self-identification,user study or survey,no,"This paper presents an analysis on identifying factors for smartphone-based data on SWB (subjective well-being) and modeling SWB changes, based on a four-month user study with 78 college students.",
Cohort Modeling Based App Category Usage Prediction,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394849,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,,
A Method to Anonymize Business Metrics to Publishing Implicit Feedback Datasets,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412256,full,yes,,,subject,no,male / female,no,self-identification,audit system behavior,yes,"However, it is difficult to publish implicit feedback datasets in a commercial service as a public dataset because there are several business risks. Implicit feedback datasets are built using user behavior logs, which include confidential business information and users’ personal information.",
Path-based Deep Network for Candidate Item Matching in Recommenders,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462878,full,yes,,,users,no,male / female,no,self-identification / annotators,gender personalization,no,"""As shown in Figure 8c, we can find that TrigNet treats gender differently to reflect the user characterisitics precisely. For example, male prefer computer, car, and watch, while women prefer flower, tourism and women shoes.""",
xLightFM: Extremely Memory-Efficient Factorization Machine,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462941,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,data obtained from Criteo and Avazu,
User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474244,full,yes,,,users,no,male / female,no,self-identification,audit system behavior / user study or survey,yes,"We further look into users’ behavior patterns like the preference of using more positive ratings, in order to interpret the observed biases. Finally, based on the observed algorithmic user bias and users’ behavior patterns, we analyze the possible factors leading to the biases and recognize problematic biases that may lead to unfairness.",
A deep learning system for predicting size and fit in fashion e-commerce,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347006,full,yes,,,subject,no,male / female / unisex,extended,inferred / annotators,gender prediction,no,inferred from purchase history,
Latent factor models and aggregation operators for collaborative filtering in reciprocal recommender systems,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347026,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,"""The dataset we used for our experiemental evaluation contained only interactions between members of opposite sexes, and we use this assumption in designing our algorithm.""",
Stereotype Modeling for Problem-Solving Performance Predictions in MOOCs and Traditional Courses,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079672,full,yes,,,users,no,male / female,no,self-identification,audit system behavior,no,,
Mitigating Sentiment Bias for Recommender Systems,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462943,full,no,contextualize argument,"""... e.g., face recognition models perform poorly on certain demographic groups defined by sex, age, and race... word embeddings pre-trained on massive text have shown a strong gender bias... """,,,,,,,,,
Vroom!: A Search Engine for Sounds by Vocal Imitation Queries,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377963,full,no,gender distribution,"""We can see that the gender distribution is quite even, an a large portion of subjects were born in the 1980s and 1990s.""",,,,,,,,,
An Eye Tracking Study of Web Search by People With and Without Dyslexia,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401103,full,no,demographic data,"""... participants answered a brief sreening and demographics questionnaire that collected information about age, gender, occupation, language fluency, education, dyslexia diagnosis... """,,,,,,,,,
Item Retrieval as Utility Estimation,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210053,full,no,demographic data,"""... we also sampled demographic information from the same survey (gender, age, income) to give more context.""",,,,,,,,,
Investigating the Influence of Personal Memories on Video-Induced Emotions,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394842,full,no,demographic data,"""We capture self-reports of the following basic features: participants’ age in years, their gender, and their nationality.""",,,,,,,,,
Learning About Work Tasks to Inform Intelligent Assistant Design,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298934,full,no,gender distribution,"""Further restrictions were based on gender and population distribution according to states and territories in Australia.""",,,,,,,,,
Neural Factorization Machines for Sparse Predictive Analytics,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080777,full,no,user attribute / profile,"""Many predictive tasks of web applications need to model categorical variables, such as user IDs and demographics like genders and occupations.""",,,,,,,,,
Controlling Spotify Recommendations: Effects of Personal Characteristics on Music Recommender User Interfaces,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209223,full,no,user attribute / profile,"""Some research only takes into account basic demographic characteristics such as age, sex and gender.""",,,,,,,,,
Susceptibility to Persuasive Strategies: A Comparative Analysis of Nigerians vs. Canadians,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209239,full,no,demographic data,"used in diagram, mentioned in future work",,,,,,,,,
Factors Influencing Privacy Concern for Explanations of Group Recommendation,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456845,full,no,user attribute / profile,"""... user personally identifiable information (e.g., gender, age, race)... """,,,,,,,,,
Incorporating Constraints into Matrix Factorization for Clothes Package Recommendation,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209228,full,no,gender distribution,"""Steps 1-3 were repeated for another user with different gender.""",,,,,,,,,
Privacy as a Planned Behavior: Effects of Situational Factors on Privacy Perceptions and Plans,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456829,full,no,demographic data,"""... participants are asked to optionally input their gender, age group, country of residence, and the duration of residence in that country.""",,,,,,,,,
”It’s like a puppet master”: User Perceptions of Personal Autonomy when Interacting with Intelligent Technologies,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456820,full,no,demographic data,"""... variation in demographics, in terms of age, gender... """,,,,,,,,,
Exploring the Effects of Natural Language Justifications in Food Recommender Systems,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456827,full,no,demographic data,used in diagram,,,,,,,,,
This Is Not What We Ordered: Exploring Why Biased Search Result Rankings Affect User Attitudes on Debated Topics,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462851,full,no,demographic data,"""Participants received a short introduction to the task and subsequently stated their gender, age, and attitude towards each of five debated topics.""",,,,,,,,,
Digital Pen Features Predict Task Difficulty and User Performance of Cognitive Tests,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394839,full,no,demographic data,"""Then, they are asked to note down their birth date, sex and handedness.""",,,,,,,,,
Who Shares Fake News in Online Social Networks?,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320456,full,no,demographic data,"""First, demographic data was collected on age, gender, and education level.""",,,,,,,,,
Using Learning Analytics to Devise Interactive Personalised Nudges for Active Video Watching,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079683,full,no,user attribute / profile,"""The metadata relates to the user profile: gender, English as native language... """,,,,,,,,,
Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462843,full,no,user attribute / profile,"""Each user has features including the user's ID, age, gender, and occupation.""",,,,,,,,,
Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331268,full,no,user attribute / profile,"""Other features are user attributes, including the user's gender, age, occupation, consumption ability... """,,,,,,,,,
Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462879,full,no,user attribute / profile,"""Other features include user ID, gender, age, and occupation.""",,,,,,,,,
Understanding and Mitigating Bias in Online Health Search,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462930,full,no,tag,"""Slight adjustments were made per specific queries, for example, if the condition was specific to a certain age group or gender.""",,,,,,,,,
TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462882,full,no,user attribute / profile,"""For example, a re-ranking algorithm is proposed in [15] that mitigates the bias of protected sensitive attributes such as gender or age.""",,,,,,,,,
Supporting Metacognition during Exploratory Search with the OrgBox,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462955,full,no,demographic data,"""Participants were also asked demographic questions: age, University status (i.e., undergrad, grad student, staff, faculty), and gender (female, male, self-identify).""",,,,,,,,,
Attentive Recurrent Social Recommendation,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210023,full,no,contextualize argument,"""... a global static preference that do not change over time (e.g., the preference that is related to each user's gender and birthplace)... """,,,,,,,,,
A Framework for Interaction-driven User Modeling of Mobile News Reading Behaviour,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209229,full,no,demographic data,"""... demographic information such as age, gender... """,,,,,,,,,
Adapting Performance And Emotional Support Feedback To Cultural Differences,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320444,full,no,contextualize argument,mentioned in related work,,,,,,,,,
Nudge your Workforce: A Study on the Effectiveness of Task Notification Strategies in Enterprise Mobile Crowdsourcing,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079692,full,no,gender distribution,"""... the company's gender distribution worldwide... """,,,,,,,,,
Auto-Suggesting Browsing Actions for Personalized Web Screen Reading,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320460,full,no,gender distribution,"""The participants varied in age... gender... """,,,,,,,,,
Personalized Recommendation of PoIs to People with Autism,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394845,full,no,contextualize argument,mentioned in related work,,,,,,,,,
Modeling and Predicting News Consumption on Twitter,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209245,full,no,user attribute / profile,"""... several demographic features (e.g., gender, age, income, and race).""",,,,,,,,,
Legal Judgment Prediction with Multi-Stage Case Representation Learning in the Real Court Setting,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462945,full,no,user attribute / profile,"""To combat these concerns, we anonymized the data by removing sensitive information (e.g., gender, race, etc.).""",,,,,,,,,
Seed-driven Document Ranking for Systematic Reviews in Evidence-Based Medicine,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3209994,full,no,user attribute / profile,"""For instance, gender/age of subjects in clinical experiment and randomized experiment design are often relevance conditions in SRs.""",,,,,,,,,
Leveraging Social Media for Medical Text Simplification,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401105,full,no,tag,"""We find that DAE model performs several lexical substitutions, such as replacing... sex-linked with gender-linked...""",,,,,,,,,
GMCM: Graph-based Micro-behavior Conversion Model for Post-click Conversion Rate Estimation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401425,full,no,user attribute / profile,"""e.g., user age, user gender, etc.""",,,,,,,,,
Do Affective Cues Validate Behavioural Metrics for Search?,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462894,full,no,gender distribution,"""Our participants also represented particular cultures, races, and genders.""",,,,,,,,,
Searching on the Go: The Effects of Fragmented Attention on Mobile Web Search Tasks,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080770,full,no,gender distribution,"""Although participants were randomly assigned to one of the 3 conditions, there was a very equal spread of genders... """,,,,,,,,,
The Role of Attributes in Product Quality Comparisons,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377956,full,no,tag,"""target gender""",,,,,,,,,
Certifiable Robustness to Discrete Adversarial Perturbations for Factorization Machines,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401087,full,no,contextualize argument,"""... a common solution is to convert them to binary features via one-hot encoding (e.g. gender of users)... """,,,,,,,,,
Investigating Users' Time Perception during Web Search,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020184,full,no,demographic data,"""... demographic questionnaire, which is about their age, gender, and familiarity with search enigne.""",,,,,,,,,
Quantifying Human-Perceived Answer Utility in Non-factoid Question Answering,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446028,full,no,demographic data,"""Participants were aksed to provide information about their age, gender, English fluency... """,,,,,,,,,
Second Chance for a First Impression? Trust Development in Intelligent System Interaction,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456817,full,no,user attribute / profile,"""... other factors did not have a significant impact, including level of education, country of origin, gender, and propensity to trust.""",,,,,,,,,
Pivoting Image-based Profiles Toward Privacy: Inhibiting Malicious Profiling with Adversarial Additions,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456832,full,no,contextualize argument,mentioned in related work,,,,,,,,,
Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462858,full,no,contextualize argument,"""Zheng et al. proposed to incorporate explicit personality traits, such as age, gender and location, into conversation.""",,,,,,,,,
Visual Re-Ranking for Multi-Aspect Information Retrieval,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020174,full,no,demographic data,"""... given a questionnaire to collect data in their age, gender, academic background and research experience.""",,,,,,,,,
Searching as Learning: Exploring Search Behavior and Learning Outcomes in Learning-related Tasks,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176386,full,no,demographic data,"""... questionnaire on demographic and background information, which included their personal details (e.g.: age and gender)... """,,,,,,,,,
Understanding Mobile Search Task Relevance and User Behaviour in Context,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298923,full,no,contextualize argument,"""They found significant differences in terms of information needs and how they were addressed depending on user gender, device and location.""",,,,,,,,,
Making Sense of Conflicting Science Information: Exploring Bias in the Search Engine Result Page,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020185,full,no,gender distribution,"""Their age range was 18-34, gender distribution was 45% female and 55% male, and 91% of participants had little to no knowledge of the topic... """,,,,,,,,,
Learning Domain Semantics and Cross-Domain Correlations for Paper Recommendation,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462975,full,no,user attribute / profile,"""Some neural network methods learn the embeddings of item tags and user attributes like gender and thus they can recommend a new item to a new user... """,,,,,,,,,
Interpretable Fashion Matching with Rich Attributes,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331242,full,no,user attribute / profile,"""We are also interested in incorporating the user profile, such as age, occupy, gender, city, social relationships, etc... """,,,,,,,,,
Legal Intelligence for E-commerce: Multi-task Learning by Leveraging Multiview Dispute Representation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331212,full,no,user attribute / profile,"""... and by removing a litigant's appearance (race, gender, weight, etc.) from a judge's consideration... """,,,,,,,,,
Understanding How People use Search to Support their Everyday Creative Tasks,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298936,full,no,demographic data,"""The survey begins with a brief demographic questionnaire (e.g., age, gender, education, field of employment).""",,,,,,,,,
Note the Highlight: Incorporating Active Reading Tools in a Search as Learning Environment,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446025,full,no,gender distribution,"""Of the valid participants, 64 identified as male, and 48 identified as female-- with 3 withholding their gender identity.""",,,,,,,,,
Searching to Learn with Instructional Scaffolding,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446012,full,no,gender distribution,"""Of the valid participants, 65 were male, 59 female (2 withheld gender information) with a median age... """,,,,,,,,,
On Understanding Data Worker Interaction Behaviors,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401059,full,no,future work / footnote / citations,footnote,,,,,,,,,
Learning Efficient Representations of Mouse Movements to Predict User Attention,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401031,full,no,user attribute / profile,"""Some studies have investigated the utility of mouse cursor data for predicting the user's emotional state, but also the extent that they can help identify demographic attributes like gender and age."" ",,,,,,,,,
"""Information Needs of the End Users Have Never Been Discussed"": An Investigation of the User-intermediary Interaction of People with Intellectual Impairments",CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377953,full,no,gender distribution,"""This corresponds with the gender distribution in this sector in Norway... """,,,,,,,,,
SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210008,full,no,user attribute / profile,"""On the other hand, our method obliterates stylistic features that could otherwise reveal the identity and other privacy-sensitive information about the writer as age or gender.""",,,,,,,,,
Online User Representation Learning Across Heterogeneous Social Networks,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331258,full,no,user attribute / profile,"""... these two attributes have reasonable granularities (i.e., not too coarse like Gender which makes the prediciton trivial... """,,,,,,,,,
The Impact of More Transparent Interfaces on Behavior in Personalized Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401117,full,no,demographic data,"""... we asked for demographic information (age and gender) and usage of news sites."" ",,,,,,,,,
What Are You Known For?: Learning User Topical Profiles with Implicit and Explicit Footprints,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080820,full,no,user attribute / profile,"""In social media systems, demographic profiles -- often including name, age, gender, and location -- provide an important first step... """,,,,,,,,,
SearchBots: User Engagement with ChatBots during Collaborative Search,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176380,full,no,tag,"""Participants were given gender neutral first names (Jamie and Taylor).""",,,,,,,,,
"Asking ""Good"" Questions: Questionnaire Design and Analysis in Interactive Information Retrieval Research",CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020167,full,no,contextualize argument,mentioned in background,,,,,,,,,
Query Suggestions as Summarization in Exploratory Search,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446020,full,no,demographic data,"""We asked users to rate their familiarity on a 4-point scale... with the following topics: robotic surgery, political bias online, sports analytics, gender recognition... """,,,,,,,,,
Evaluating Mobile Search with Height-Biased Gain,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080795,full,no,demographic data,"""... complete a demographic questionnaire, which investigates their age, gender, major... """,,,,,,,,,
Investigating Expectations for Voice-based and Conversational Argument Search on the Web,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377978,full,no,gender distribution,"""The gender distribution has been similar though, with 67% male and 33% female participants.""",,,,,,,,,
Intent-aware Query Obfuscation for Privacy Protection in Personalized Web Search,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3209983,full,no,contextualize argument,"""According to Jones et al.'s study in [28], a simple supervised classifier based on the textual query content recorded in search engine logs can link a sequence of queries to a set of candidate users with known gender, age and locastion... """,,,,,,,,,
Everyday Cross-session Search: How and Why Do People Search Across Multiple Sessions?,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377970,full,no,demographic data,"""We also asked demographic questions (i.e., age, gender, education level, occupation).""",,,,,,,,,
Adversarial-Enhanced Hybrid Graph Network for User Identity Linkage,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462946,full,no,user attribute / profile,"""The most straightforward solution is to utilize the user's profile information, such as usernames, genders and birthdays.""",,,,,,,,,
Optimally balancing receiver and recommended users' importance in reciprocal recommender systems,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240349,full,no,user attribute / profile,"""... attributes of the user from her public profile, for example: age, gender, height, profession... """,,,,,,,,,
Designing for the better by taking users into account: a qualitative evaluation of user control mechanisms in (news) recommender systems,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347014,full,no,gender distribution,"""Participants were equally divided in gender, age ranged from... """,,,,,,,,,
PrivateJobMatch: a privacy-oriented deferred multi-match recommender system for stable employment,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346983,full,no,user attribute / profile,"""DAA was initially introduced for the stable marriage problem... given n men and n women, where each person has ranked all the memebers of the opposite sex in order of preference, determine the marriages that are stable.. """,,,,,,,,,
An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changes,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474241,full,no,user attribute / profile,"""The gender was set as ""rather not say"" to prevent any personalization based on gender.""",,,,,,,,,
Explaining and exploring job recommendations: a user-driven approach for interacting with knowledge-based job recommender systems,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347001,full,no,user attribute / profile,"""Factors that are taken into account were age, gender, and background.""",,,,,,,,,
No more ready-made deals: constructive recommendation for telco service bundling,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240348,full,no,demographic data,"""Participants who interacted with the three wersions of the system were not signifcantly different by gender, age, and possession of a phone plan.""",,,,,,,,,
Offline Contextual Multi-armed Bandits for Mobile Health Interventions: A Case Study on Emotion Regulation,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412244,full,no,gender distribution,"""... 81 female, 29 male (no participants reported a non-bonary gender identity)... """,,,,,,,,,
"The role of preference consistency, defaults and musical expertise in users’ exploration behavior in a genre exploration recommender",RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474253,full,no,gender distribution,"""The factors MSE, gender and age are excluded due to non-significant effects.""",,,,,,,,,
Recommending Product Sizes to Customers,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109891,full,no,user attribute / profile,"""... by leveraging additional information in the form of user features such as age, gender, Prime subscription... """,,,,,,,,,
Effects of personal characteristics on music recommender systems with different levels of controllability,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240358,full,no,demographic data,"""240 valid participants... Gender: Female = 55.42%... """,,,,,,,,,
SSE-PT: Sequential Recommendation Via Personalized Transformer,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412258,full,no,demographic data,used in diagram,,,,,,,,,
“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474232,full,no,demographic data,"""... as well as to disclose some demographic details, such as age and gender.""",,,,,,,,,
Stronger Privacy for Federated Collaborative Filtering With Implicit Feedback,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474262,full,no,contextualize argument,"""Some of these studies highlight how even non-sensitive data like movie ratings can be used to infer age, gender, and political affiliation of users.""",,,,,,,,,
Follow the guides: disentangling human and algorithmic curation in online music consumption,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474269,full,no,contextualize argument,"""... for instance... categorical variables like gender... """,,,,,,,,,
Making Neural Networks Interpretable with Attribution: Application to Implicit Signals Prediction,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412253,full,no,user attribute / profile,"""... CF is more difficulat to interpret than a content-based method that would only leverage the provided descriptive features for users - age range, gender, occupation - and movies... """,,,,,,,,,
Discovering Hidden Course Requirements and Student Competences from Grade Data,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099034,full,no,contextualize argument,mentioned in related work,,,,,,,,,
Enhancing structural diversity in social networks by recommending weak ties,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240371,full,no,user attribute / profile,"""... (e.g., cultural diversity, professional diversity, gender, age, etc.)... """,,,,,,,,,
Comfride: a smartphone based system for comfortable public transport recommendation,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240359,full,no,contextualize argument,"""... and individuals differ widely in their perception of comfort primarily depending on their age and gender.""",,,,,,,,,
Emotion Detection through Smartphone's Accelerometer and Gyroscope Sensors,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456822,full,no,demographic data,"""... and 2 people who preferred not to state their gender.""",,,,,,,,,
Predictive Student Modeling in Block-Based Programming Environments with Bayesian Hierarchical Models,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394853,full,no,gender distribution,"""... reporting their gender as female.""",,,,,,,,,
Effects of Individual Traits on Diversity-Aware Music Recommender User Interfaces,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209225,full,no,gender distribution,"""... Gender: 45.6% female... """,,,,,,,,,
A User Study on Groups Interacting with Tourist Trip Recommender Systems in Public Spaces,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320449,full,no,gender distribution,"""One participant preferred to not comment on gender.""",,,,,,,,,
Eliciting Touristic Profiles: A User Study on Picture Collections,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394868,full,no,demographic data,"""Q09 - What is your gender?""",,,,,,,,,
Calibrated recommendations,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240372,full,no,user attribute / profile,"""... e.g., based on gender, race, age, etc.""",,,,,,,,,
cDLRM: Look Ahead Caching for Scalable Training of Recommendation Models,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474246,full,no,user attribute / profile,"""Typically, the continuous features represent user information, such as age, gender, and the categorical features... """,,,,,,,,,
Who is Your Best Friend?: Ranking Social Network Friends According to Trust Relationship,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209243,full,no,user attribute / profile,"""We can see that these users are diverse in gender, race, age and educational background.""",,,,,,,,,
Adaptive City Characteristics: How Location Familiarity Changes What Is Regionally Descriptive,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079665,full,no,gender distribution,"""There are no significant differences in our findings based on gender or age of participants.""",,,,,,,,,
ContextPlay: Evaluating User Control for Context-Aware Music Recommendation,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320445,full,no,demographic data,"""This questionnaire asks the user's age and gender, and measures musical sophistication.""",,,,,,,,,
Privacy Preserving Collaborative Filtering by Distributed Mediation,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474251,full,no,contextualize argument,mentioned in related work,,,,,,,,,
Scaffolding for an OLM for Long-Term Physical Activity Goals,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209220,full,no,demographic data,"""... details of our participants, ordered by gender... """,,,,,,,,,
Exploring Personalized University Ranking and Recommendation,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397590,full,no,gender distribution,"""... and 3 people refused to disclose their gender.""",,,,,,,,,
Modeling Tourists' Personality in Recommender Systems: How Does Personality Influence Preferences for Tourist Attractions?,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394843,full,no,demographic data,"""sex"" used in table",,,,,,,,,
Keeping Dataset Biases out of the Simulation: A Debiased Simulator for Reinforcement Learning based Recommender Systems,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412252,full,no,user attribute / profile,"""... profile of users (e.g., gender and age)... """,,,,,,,,,
I just scroll through my stuff until I find it or give up: A Contextual Inquiry of PIM on Private Handheld Devices,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176394,full,no,contextualize argument,"""... while Andone et al. [1] analyzed age and gender differences in smartphone usage through a longitudinal survey study.""",,,,,,,,,
CB2CF: a neural multiview content-to-collaborative filtering model for completely cold item recommendations,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347038,full,no,tag,"""The second example demonstrates a transition from versatile actors to comedy-oriented actors in both genders.""",,,,,,,,,
EX3: Explainable Attribute-aware Item-set Recommendations,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474240,full,no,tag,used in table,,,,,,,,,
Nonlinear Robust Discrete Hashing for Cross-Modal Retrieval,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401152,full,N/A,,,,,,,,,,,
We are the Change that we Seek: Information Interactions During a Change of Viewpoint,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377975,full,N/A,,"""Changed view on whether he thought Michael Jackson was likely guilty of child sexual abuse""",,,,,,,,,
LuckyFind: Leveraging Surprise to Improve User Satisfaction and Inspire Curiosity in a Recommender System,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446017,full,N/A,,"""One example is that a participant found an article that claimed that over-weight women tend to have a stronger sex drive.""",,,,,,,,,
Fight Fire with Fire: Towards Robust Recommender Systems via Adversarial Poisoning Training,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462914,full,N/A,,"""... (e.g., Amazon's online retailer attached a link to a sex manual next to the spiritual guide by constructing some fake ratings).""",,,,,,,,,
From Royals to Vegans: Characterizing Question Trolling on a Community Question Answering Website,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210058,full,N/A,,"""... the troll terms for both title and description include adult words ('sex', 'panties', 'naked), profanity...""",,,,,,,,,
User Interests in German Social Science Literature Search: A Large Scale Log Analysis,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020168,full,N/A,,"""On the fist level important user terms are discrimination, racism, stigmatization... sexism, homophobia, homosexuality, women, group-focused, sexual, antiziganism... """,,,,,,,,,
Table Search Using a Deep Contextualized Language Model,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401044,full,N/A,,used as example,,,,,,,,,
Ranking Documents by Answer-Passage Quality,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210028,full,N/A,,"""... Korean does not conjugate verbs using agreement with the subject, and nouns have no gender."" ",,,,,,,,,
Creating a Children-Friendly Reading Environment via Joint Learning of Content and Human Attention,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401062,full,N/A,,"""Children's curiosity and adolescence's hormone spike can trigger their energetic exploration and discovery of sexual information.""",,,,,,,,,
Few-Shot Conversational Dense Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462856,full,N/A,,"""How do sexual and asexual reproduction affect [Darwin's Theory]?""",,,,,,,,,
Supervised Hierarchical Cross-Modal Hashing,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331229,full,N/A,,"""Yoins Sexy Red Lace Baackless Mini Dress""",,,,,,,,,
Multi-Type Textual Reasoning for Product-Aware Answer Generation,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462899,full,N/A,,"""Make you beautiful, fashionable, sexy and elegant.""",,,,,,,,,
Learning to Represent Human Motives for Goal-directed Web Browsing,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474260,full,N/A,,"""Sex & Romance"" as goal category in web browsing",,,,,,,,,
Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401156,full,applied,user attribute / profile,"""... self-supervised learned user representation can be used to infer user profiles, such as for instance the gender, age, preferences and life status... """,,,,,,,,,
ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401043,full,applied,user attribute / profile,"""Each group is composed of some sparse features: user profile contains the user id, age, gender, etc; user's behavior... """,,,,,,,,,
Measuring and Mitigating Item Under-Recommendation Bias in Personalized Ranking Systems,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401177,full,applied,vectorized / grouped,"""A group here could correspond to gender, ethnicity, or other item attributes.""",,,,,,,,,
AutoGroup: Automatic Feature Grouping for Modelling Explicit High-Order Feature Interactions in CTR Prediction,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401082,full,applied,vectorized / grouped,"""An embedding layer is applied to compress the raw features to low-dimensional vectors before feeding them into neural networks. For a univalent field, (e.g., ""Gender=Male"")... """,,,,,,,,,
"One Person, One Model, One World: Learning Continual User Representation without Forgetting",SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462884,full,applied,user attribute / profile,"""In our CL setting, [a given set of consecutive tasks] can be different tasks, including various profile (e.g., gender) prediciton and item recommendation tasks... """,,,,,,,,,
Adaptive Modelling of Attentiveness to Messaging: A Hybrid Approach,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320461,full,applied,vectorized / grouped,"""...  group-modeling based on age and gender does not provide an improvement over our general model.""",,,,,,,,,
Neural Graph Matching based Collaborative Filtering,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462833,full,applied,user attribute / profile,"""For example, (Male, 1) and (Female, 1) mean the user's gender is Male and Female, respectively, where [these variables] are considered as two user attributes"" in attribute-value pair.",,,,,,,,,
FORM: Follow the Online Regularized Meta-Leader for Cold-Start Recommendation,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462831,full,applied,user attribute / profile,"""User features include user identifier and other contents such as gender and profession... """,,,,,,,,,
Automated Comparative Table Generation for Facilitating Human Intervention in Multi-Entity Resolution,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210021,full,applied,user attribute / profile,"""Each entity is described by hundreds of properties and values, and some of them are very similar, e.g., types, names and genders, which make automated ER approaches difficult to decide whether all the three entities refer to the same person or not.""
",,,,,,,,,
Comparing In Situ and Multidimensional Relevance Judgments,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080840,full,applied,user attribute / profile,"""All six models also include the same set of control variables, including: gender (Male or Female), age (four levels... """,,,,,,,,,
An Image is Worth a Thousand Terms? Analysis of Visual E-Commerce Search,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462950,full,applied,demographic data,"""For gender, we observed a substantially higher portion of female searchers for visual search... """,,,,,,,,,
User Behavior Retrieval for Click-Through Rate Prediction,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401440,full,applied,user attribute / profile,"""There are features of the prediction target, such as the user's location, gender, occupation, and item's category... """,,,,,,,,,
ATBRG: Adaptive Target-Behavior Relational Graph Network for Effective Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401428,full,applied,user attribute / profile,"""... each user u is associated with a user profile xu consisting of sparse features (e.g., user id and gender)... """,,,,,,,,,
Policy-Gradient Training of Fair and Unbiased Ranking Functions,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462953,full,applied,vectorized / grouped,"""A group is simply a collection of items by any criterion, such as gender, price, brand, etc.""",,,,,,,,,
Opportunistic Multi-aspect Fairness through Personalized Re-ranking,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394846,full,applied,user attribute / profile,"""After preparing the data, the final features for each loan reduced to borrower’s gender, borrower’s country, loan purpose... """,,,,,,,,,
BiANE: Bipartite Attributed Network Embedding,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401068,full,applied,user attribute / profile,"""Nodes may have attributes, such as user profiles (e.g., gender, age, occupation, location)... """,,,,,,,,,
Generative Attribute Manipulation Scheme for Flexible Fashion Search,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401150,full,applied,user attribute / profile,used in table,,,,,,,,,
ScaleFreeCTR: MixCache-based Distributed Training System for CTR Models with Huge Embedding Table,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462976,full,applied,vectorized / grouped,"""The embedding layer transforms the high-dimensional sparse input (which are usually categorical features, such as city, gender, user id) into low-dimensional dense real-value vectors.""",,,,,,,,,
A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462842,full,applied,vectorized / grouped,"""... xi is a one-hot feature representation of the i-th field, which is categorical (e.g., gender=male, name=Ala, age=25). """,,,,,,,,,
Controlling Fairness and Bias in Dynamic Learning-to-Rank,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401100,full,applied,vectorized / grouped,"""These groups can be legally protected groups (e.g., gender, race), reflect some other strucutre... """,,,,,,,,,
Fairness among New Items in Cold Start Recommender Systems,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462948,full,applied,vectorized / grouped,"""The goal is to ensure that items from different groups can be equally recommended to matched users during testing... for example, candidates of different genders are equally recommended to job openings that they are qualified for.""",,,,,,,,,
Graph Embedding Based Recommendation Techniques on the Knowledge Graph,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099096,full,applied,user attribute / profile,"""The node of the colour grey represents the gender of a person.""",,,,,,,,,
Exploring Mental Models for Transparent and Controllable Recommender Systems: A Qualitative Study,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394841,full,applied,user attribute / profile,"""Regarding the acquisition of data in step (1), our analysis revealed that participants considered user characteristics, such as location, gender, and age, as well as user interaction behavior as relevant for Netflix.""",,,,,,,,,
Fairness-Aware Explainable Recommendation over Knowledge Graphs,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401051,full,applied,vectorized / grouped,"Existing research on fairness has shown that protected groups, defined as the population of vulnerable individuals in terms of sensitive features such as gender, age, race, religion, etc.""",,,,,,,,,
Data-Driven Modeling of Learners’ Individual Differences for Predicting Engagement and Success in Online Learning,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456834,full,applied,vectorized / grouped,"""In essence, we wanted to augment various dimensions of incoming individual differences already present in our dataset (i.e., gender, pre-test scores, SE and KMA)... """,,,,,,,,,
Comparing Peer Recommendation Strategies in a MOOC,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099036,full,applied,vectorized / grouped,"""In particular, we considered the 6 following variables: gender, country (grouped per sub-continents)... """,,,,,,,,,
Where To Go Next?: Exploiting Behavioral User Models in Smart Environments,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079687,full,applied,user attribute / profile,"""These preferences are perspectives of the narratives, language, gender and the user's age range.""",,,,,,,,,
Attribute-aware non-linear co-embeddings of graph features,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346999,full,applied,vectorized / grouped,vectorized with age and occupation,,,,,,,,,
Translation-based factorization machines for sequential recommendation,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240356,full,applied,user attribute / profile,"""We use the following features in our models: user age, user gender, user occupation... """,,,,,,,,,
Eliciting pairwise preferences in recommender systems,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240364,full,applied,user attribute / profile,"""The model generates recommendations using the user 's age and gender (if available), contextual information... """,,,,,,,,,
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412233,full,applied,user attribute / profile,"""For the static features like gender, each feature is processed by an independent embedding layer."" ",,,,,,,,,
Personalized re-ranking for recommendation,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347000,full,applied,vectorized / grouped,"""The side information of user includes gender, age and purchasing level.""",,,,,,,,,
Adversarial attacks on an oblivious recommender,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347031,full,applied,vectorized / grouped,"""... similar omitted results hold for groups based on gender, age.""",,,,,,,,,
The Influence of Personality on Mobile Web Credibility,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099074,LBR,no,demographic data,"""Moreover, we found no moderation of the relationships in the model by gender or age or level of education.""",,,,,,,,,
Polarization Effects in Group Decisions,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225242,LBR,no,future work / footnote / citations,,,,,,,,,,
You've Got a Friend in Me: Children and Search Agents,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397604,LBR,no,future work / footnote / citations,"""We did not examine children’s preferences based on gender... """,,,,,,,,,
"On the Relations Between Cooking Interests, Hobbies and Nutritional Values of Online Recipes: Implications for Health-Aware Recipe Recommender Systems",UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099072,LBR,no,contextualize argument,mentioned in related work,,,,,,,,,
Study on Motivating Physical Activity in Children with Personalized Gamified Feedback,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225227,LBR,no,demographic data,"""The avatar is represented by two animation figures from current children movies depending on the gender of the participant.""",,,,,,,,,
Privacy Perceiver: Using Social Network Posts to Derive Users' Privacy Measures,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225228,LBR,no,tag,used in table,,,,,,,,,
A Stable Personalised Partner Selection for Collaborative Privacy Education,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397597,LBR,no,contextualize argument,mentioned in related work,,,,,,,,,
Exploring Online Music Listening Behaviors of Musically Sophisticated Users,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324974,LBR,no,contextualize argument,mentioned in related work,,,,,,,,,
Getting to Know Your Neighbors (KYN). Explaining Item Similarity in Nearest Neighbors Collaborative Filtering Recommendations,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397599,LBR,no,contextualize argument,mentioned in introduction,,,,,,,,,
Predicting Successful Collaboration in a Pair Programming Eye Tracking Experiment,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225234,LBR,no,demographic data,"""... we randomly paired regardless of gender and experience... """,,,,,,,,,
A Decentralized Recommendation Engine in the Social Internet of Things,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397602,LBR,no,contextualize argument,"attribute offered by dataset, not used",,,,,,,,,
"""OMG! How did it know that?"": Reactions to Highly-Personalized Ads",UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3101411,LBR,no,gender distribution,"""... our sample is gender-balanced.""",,,,,,,,,
User Interfaces for Counteracting Decision Manipulation in Group Recommender Systems,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324977,LBR,no,future work / footnote / citations,mentioned in future work,,,,,,,,,
The Influence of Culture in the Effect of Age and Gender on Social Influence in Persuasive Technology,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099071,LBR,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,yes,"Our findings provide designers of gamified persuasive applications with empirical insights, including a number of guidelines, for tailoring to the individualist and collectivist cultures based on age and gender. ",
Personalizing Persuasive Technologies: Do Gender and Age Affect Susceptibility to Persuasive Strategies?,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225246,LBR,yes,,,users,no,male / female,no,self-identification,gender personalization / user study or survey,no,"In this work, we focused on African audience to investigate how individual’s responsiveness to three persuasive strategies (Reward, Social Learning, and Social Comparison) varies by Gender and Age group via a large-scale study of 712 participants.",
"Photos Don't Have Me, But How Do You Know Me?: Analyzing and Predicting Users on Instagram",UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225232,LBR,yes,,,users,no,male / female,no,annotators,gender prediction,no,,
Assessing Objective Indicators of Users' Cognitive Load During Proactive In-Car Dialogs,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324985,LBR,yes,,,users,no,male / female,no,self-identification,user study or survey,no,We assessed the users’ CL during the interaction with the PA by employing these data as well as realtime driving data (RTDA) via the Controller Area Network (CAN bus). ,
The Effect of Smiling Pictures on Perceptions of Personas,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324973,LBR,yes,,,subject,yes,male / female,no,annotators,persona generation / user study or survey,no,user perception of personas,
Socially Responsive eCommerce Platforms: Design Implications for Online Marketplaces in Developing African Nation,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324984,LBR,applied,demographic data,"""In addition, the analysis of the user-based study (survey) shows that 90% of the participants (91 subjects) across both genders strongly agreed to the eleven items in the questionnaire... """,,,,,,,,,
Recommenders with a Mission: Assessing Diversity in News Recommendations,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446019,perspective,no,contextualize argument,"""Though there are a number of studies that aim to detect certain characteristics of minorities from textual data, such as predicting a person's ethnicity and gender based on their first and last name... """,,,,,,,,,
Lady Chatterley's Library: Books and Reading as Public Performance and Private Act,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446032,perspective,no,contextualize argument,"""Recent research has shown that the impact of gender on choice of reading material is reduced in the context of digital reading... """,,,,,,,,,
Technology-facilitated Societal Consensus,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3323451,perspective,no,contextualize argument,"""...for example the legal recognition of same-sex marriages... """,,,,,,,,,
Making Meaning: A Focus for Information Interactions Research,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298938,perspective,N/A,,"""... portrayals of transgendered characters are not always positive..."" & no model",,,,,,,,,
Experimental Methods in IIR: The Tension between Rigour and Ethics in Studies Involving Users with Dyslexia,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298939,perspective,applied,demographic data,"""Any demographic information e.g. gender can also be used as an extra dimsension of analysis.""",,,,,,,,,
Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401443,perspective,applied,user attribute / profile,"""The user features incluse users' ID, ages, genders and purchasing powers, etc.""",,,,,,,,,
Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401446,perspective,applied,user attribute / profile,"""DPSR-p refers to a basic personalized verson of our model, with additional user profile features, like purchase power, gender and so on.""",,,,,,,,,
Learning from Multi-annotator Data: A Noise-aware Classification Framework,TOIS19,https://dl.acm.org/doi/10.1145/3309543,journal,yes,,,annotators,no,male / female,no,self-identification,user study or survey,yes,"""However, people from different social and knowledge backgrounds have different views on various texts, which may lead to noisy labels.""",
User Modeling on Demographic Attributes in Big Mobile Social Networks,TOIS17,https://dl.acm.org/doi/10.1145/3057278,journal,yes,,,users,no,male / female,no,inferred,gender prediction,no,,
User Profiling Based on Nonlinguistic Audio Data,TOIS22,https://dl.acm.org/doi/10.1145/3474826,journal,yes,,,users,no,male / female,no,inferred,gender prediction,no,,
What and How long: Prediction of Mobile App Engagement,TOIS22,https://dl.acm.org/doi/10.1145/3464301,journal,yes,,,users,no,male / female,no,self-identification,user study or survey,no,based on user behavior (engagement) and how we can predict it,
An Enhanced Neural Network Approach to Person-Job Fit in Talent Recruitment,TOIS20,https://dl.acm.org/doi/10.1145/3376927,journal,yes,,,users,no,male / female,no,self-identification,audit system behavior,yes,(profile may self id),
Understanding and Leveraging the Impact of Response Latency on User Behaviour in Web Search,TOIS18,https://dl.acm.org/doi/10.1145/3106372,journal,yes,,,users,no,male / female,no,self-identification,user study or survey,no,analyze latency (empirically and otherwise) and offer framework,
Product-Based Neural Networks for User Response Prediction over Multi-Field Categorical Data,TOIS19,https://dl.acm.org/doi/10.1145/3233770,journal,yes,,,users,no,male / female,no,self-identification,gender personalization,no,,
Component-based Analysis of Dynamic Search Performance,TOIS22,https://dl.acm.org/doi/10.1145/3483237,journal,no,contextualize argument,"""Roitero et al. [63] used ANOVA to model the effects of user attributes such as user age, profile age, and gender... """,,,,,,,,,
Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance,TOIS22,https://dl.acm.org/doi/10.1145/3474055,journal,no,contextualize argument,mentioned in future work,,,,,,,,,
Theories of Conversation for Conversational IR,TOIS21,https://dl.acm.org/doi/10.1145/3439869,journal,no,contextualize argument,"(referring to computers w/ personalities) ""we also apply human stereotypes, such as those around gender... """,,,,,,,,,
Profiling Users for Question Answering Communities via Flow-Based Constrained Co-Embedding Model,TOIS22,https://dl.acm.org/doi/10.1145/3470565,journal,no,contextualize argument,"""Farnadi et al. [19] propose a mechanism to infer a variety of user characteristics, such as age, gender, and personality traits... """,,,,,,,,,
Integrating Collaboration and Leadership in Conversational Group Recommender Systems,TOIS21,https://dl.acm.org/doi/10.1145/3462759,journal,no,demographic data,"""... personal information such as name, gender, educational level, degree of relationship with other group members, and age.""",,,,,,,,,
Mining Exploratory Behavior to Improve Mobile App Recommendations,TOIS17,https://dl.acm.org/doi/10.1145/3072588,journal,no,demographic data,"""... and demographic variables such as age and gender.""",,,,,,,,,
Investigating Searchers’ Mental Models to Inform Search Explanations,TOIS20,https://dl.acm.org/doi/10.1145/3371390,journal,no,demographic data,"""Our participants were selected with an attempt to balance for age and gender... """,,,,,,,,,
Understanding Faceted Search from Data Science and Human Factor Perspectives,TOIS19,https://dl.acm.org/doi/10.1145/3284101,journal,no,demographic data,used in table,,,,,,,,,
Attentive Long Short-Term Preference Modeling for Personalized Product Search,TOIS19,https://dl.acm.org/doi/10.1145/3295822,journal,no,demographic data,"""It is inherently correlated with the user's background (e.g., gender, age, career, or consumption capability).""",,,,,,,,,
Effects of Personalized and Aggregate Top-N Recommendation Lists on User Preference Ratings,TOIS21,https://dl.acm.org/doi/10.1145/3430028,journal,no,demographic data,"""... participant age (integer), gender (binary)... """,,,,,,,,,
Keeping the Data Lake in Form: Proximity Mining for Pre-Filtering Schema Matching,TOIS20,https://dl.acm.org/doi/10.1145/3388870,journal,no,user attribute / profile,"""The datasets will have similar attributes (partially) overlapping their information like the patient’s age, gender, and some common laboratory tests like blood samples.""",,,,,,,,,
Spoken Conversational Context Improves Query Auto-completion in Web Search,TOIS21,https://dl.acm.org/doi/10.1145/3447875,journal,no,user attribute / profile,"""... profile context such as age and gender... """,,,,,,,,,
Deep Item-based Collaborative Filtering for Top-N Recommendation,TOIS19,https://dl.acm.org/doi/10.1145/3314578,journal,no,user attribute / profile,"""... discrete features (e.g., user gender and item attributes)... """,,,,,,,,,
A Price-per-attention Auction Scheme Using Mouse Cursor Information,TOIS20,https://dl.acm.org/doi/10.1145/3374210,journal,no,user attribute / profile,"""Therefore, we cannot conclude that user's gender plays an important role in predicting user attention to online ads and, subsequently, gender should not be used to inform the online auction.""",,,,,,,,,
Challenges in Building Intelligent Open-domain Dialog Systems,TOIS20,https://dl.acm.org/doi/10.1145/3383123,journal,no,user attribute / profile,"""The personal profile of each user is collected, which includes five personality traits: Gender, Age, Location, Interest Tags, and Self Description.""",,,,,,,,,
Next and Next New POI Recommendation via Latent Behavior Pattern Inference,TOIS19,https://dl.acm.org/doi/10.1145/3354187,journal,no,user attribute / profile,"""... because LBSN users vary largely with respect to diverse features, such as age, gender, home city, and occupation.""",,,,,,,,,
"Suggesting Points-of-Interest via Content-Based, Collaborative, and Hybrid Fusion Methods in Mobile Devices",TOIS18,https://dl.acm.org/doi/10.1145/3125620,journal,no,user attribute / profile,"""Some of this information seems correlated to profile POIs, e.g., category tags, age, gender... """,,,,,,,,,
Personalized Context-Aware Point of Interest Recommendation,TOIS18,https://dl.acm.org/doi/10.1145/3231933,journal,no,user attribute / profile,"""... we include two types of features: (1) location based... (2) user based: age group and gender.""",,,,,,,,,
HyperSoRec: Exploiting Hyperbolic User and Item Representations with Multiple Aspects for Social-aware Recommendation,TOIS22,https://dl.acm.org/doi/10.1145/3463913,journal,no,user attribute / profile,"""... the aspects can be defined as users' profiles (e.g., gender, age)... """,,,,,,,,,
"Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations",TOIS21,https://dl.acm.org/doi/10.1145/3426723,journal,no,user attribute / profile,"""... consider the user-side contexts, e.g., age, gender, and location.""",,,,,,,,,
Why or Why Not? The Effect of Justification Styles on Chatbot Recommendations,TOIS21,https://dl.acm.org/doi/10.1145/3441715,journal,no,demographic data,"""We adapted items for gender based on recent recommendations on gender inclusion in surveys.""",,,,,,,,,
Does Diversity Affect User Satisfaction in Image Search,TOIS19,https://dl.acm.org/doi/10.1145/3320118,journal,no,tag,"""However, the annotation of content diversity mainly focuses on the shape of the haircuts of the gender of the models.""",,,,,,,,,
Tweet Can Be Fit: Integrating Data from Wearable Sensors and Multiple Social Networks for Wellness Profile Learning,TOIS17,https://dl.acm.org/doi/10.1145/3086676,journal,no,tag,"used in table ""Gender labels""",,,,,,,,,
Fine-Grained Privacy Detection with Graph-Regularized Hierarchical Attentive Representation Learning,TOIS20,https://dl.acm.org/doi/10.1145/3406109,journal,no,tag,"""Users’ gender information can be embedded in their roles in relationships (e.g., daughter and girlfriend) or the distinct gender characteristic (e.g., period for women).""",,,,,,,,,
Question Tagging via Graph-guided Ranking,TOIS22,https://dl.acm.org/doi/10.1145/3468270,journal,no,tag,"""gender bias""",,,,,,,,,
Large-Scale Question Tagging via Joint Question-Topic Embedding Learning,TOIS20,https://dl.acm.org/doi/10.1145/3380954,journal,no,tag,used in table,,,,,,,,,
Inferring Dynamic User Interests in Streams of Short Texts for User Clustering,TOIS18,https://dl.acm.org/doi/10.1145/3072606,journal,no,tag,used in table,,,,,,,,,
MyrrorBot: A Digital Assistant Based on Holistic User Models for Personalized Access to Online Services,TOIS21,https://dl.acm.org/doi/10.1145/3447679,journal,applied,user attribute / profile,user feature 'sex' in user profile table,,,,,,,,,
The Characteristics of Voice Search: Comparing Spoken with Typed-in Mobile Web Search Queries,TOIS18,https://dl.acm.org/doi/10.1145/3182163,journal,applied,user attribute / profile,"""Each query in the log, either voice or text, included, in addition to the query itself, a timestamp... and, for loggin-in users, the user's age and gender.""",,,,,,,,,
FNED: A Deep Network for Fake News Early Detection on Social Media,TOIS20,https://dl.acm.org/doi/10.1145/3386253,journal,applied,user attribute / profile,"""... added some unique user features that are supported by Sina Weibo, a Chinese social media platform, e.g., gender and registration place... """,,,,,,,,,
"Search, Mining, and Their Applications on Mobile Devices: Introduction to the Special Issue",TOIS17,https://dl.acm.org/doi/10.1145/3086665,journal,applied,user attribute / profile,"""... a probabilistic factor graph model is developed to expoit the dependency between network features and users' gender and age attributes.""",,,,,,,,,
Social Context-aware Person Search in Videos via Multi-modal Cues,TOIS22,https://dl.acm.org/doi/10.1145/3480967,journal,applied,vectorized / grouped,"""... we extract the gender features, as well as age features and activity features... A calibrated support vector machine (SVM) combining all features above... """,,,,,,,,,
A Deep Learning Architecture for Psychometric Natural Language Processing,TOIS20,https://dl.acm.org/doi/10.1145/3365211,journal,applied,vectorized / grouped,"""... we included user age and gender as additional classification tasks for evaluating PyNDA and comparison methods.""",,,,,,,,,
VM-NSP: Vertical Negative Sequential Pattern Mining with Loose Negative Element Constraints,TOIS21,https://dl.acm.org/doi/10.1145/3440874,journal,N/A,,,,,,,,,,,
DeepMob: Learning Deep Knowledge of Human Emergency Behavior and Mobility from Big and Heterogeneous Data,TOIS17,https://dl.acm.org/doi/10.1145/3057280,journal,N/A,,,,,,,,,,,
Seed-Guided Topic Model for Document Filtering and Classification,TOIS19,https://dl.acm.org/doi/10.1145/3238250,journal,N/A,,,,,,,,,,,
An Attention-based Deep Relevance Model for Few-shot Document Filtering,TOIS21,https://dl.acm.org/doi/10.1145/3419972,journal,N/A,,,,,,,,,,,
Explicit Diversification of Event Aspects for Temporal Summarization,TOIS18,https://dl.acm.org/doi/10.1145/3158671,journal,N/A,,,,,,,,,,,
"We Could, but Should We?: Ethical Considerations for Providing Access to GeoCities and Other Historical Digital Collections",CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377980,perspective,no,contextualize argument,"""... a piece of content uploaded by an individual may be designated for women only."" ",,,,,,,,,
"Reflecting upon Perceptual Speed Tests in Information Retrieval: Limitations, Challenges, and Recommendations",CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377982,perspective,no,gender distribution,"""54 females""",,,,,,,,,
Ensembles of Recurrent Networks for Classifying the Relationship of Fake News Titles,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331305,short,N/A,,,,,,,,,,"counted ""men-tioned""",
DeepStyle: Learning User Preferences for Visual Recommendation,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080658,short,yes,,,subject,no,male / female,no,annotators,gender personalization,no,Amazon dataset,
Emotional Social Signals for Search Ranking,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080718,short,no,tag,"""X-Men""",,,,,,,,can't find mention of any keywords...,
Evolution of Information Needs based on Life Event Experiences with Topic Transition,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080703,short,no,future work / footnote / citations,"""The annotators were male college students.""",,,,,,,,,
Identifying and Modeling Information Resumption Behaviors in Cross-Device Search,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210126,short,no,gender distribution,"""... (22 females and 12 males)... """,,,,,,,,,
ECG Data Modeling and Analyzing via Deep Representation Learning and Nonparametric Hidden Markov Models,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463044,short,no,demographic data,"""The ECGFiveDays was sampled from a 67 year old male with 136 time steps... """,,,,,,,,,
Analysis of Children's Queries and Click Behavior on Ranked Results and Their Thought Processes in Google Search,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022157,short,no,demographic data,"""... demographics and background are diverse (e.g., male, female... """,,,,,,,,,
Impact of Response Latency on User Behaviour in Mobile Web Search,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446038,short,no,gender distribution,"""... (female=14, male=16)... """,,,,,,,,,
What Sources to Rely on:: Laypeople's Source Selection in Online Health Information Seeking,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176881,short,no,gender distribution,"""... (15 females and 9 males... """,,,,,,,,,
Do Highlights Affect Comprehension?: Lessons from a User Study,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022158,short,no,gender distribution,"""... (14 males, 15 females)... """,,,,,,,,,
Conversational vs Traditional: Comparing Search Behavior and Outcome in Legal Case Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463064,short,no,gender distribution,"""... (41 males and 69 females)... """,,,,,,,,,
The Effects of Working Memory during Search Tasks of Varying Complexity,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298948,short,no,gender distribution,"""... (18 females).""",,,,,,,,,
Personalizing Information Retrieval Using Search Behaviors and Time Constraints,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176878,short,no,gender distribution,"""... (20 females and 20 males)... """,,,,,,,,,
Noisy Signals: Understanding the Impact of Auditory Distraction on Web Search Tasks,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176871,short,no,gender distribution,"""... of whom 10 were male... """,,,,,,,,,
Challenges and Supports for Accessing Open Government Datasets: Data Guide for Better Open Data Access and Uses,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298958,short,no,gender distribution,"""... (3 females and 11 males... """,,,,,,,,,
Exploring Email Triage: Challenges and Opportunities,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298960,short,no,gender distribution,"""... and 37% of them were females.""",,,,,,,,,
"Relationships between Age, Domain Knowledge and Prior Knowledge Pre-activation on Information Searching",CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022135,short,no,gender distribution,"""... 5 males and 21 females... """,,,,,,,,,
Investigating Information Seekers' Selection of Interpersonal and Impersonal Sources,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022151,short,no,gender distribution,"""... 27 were female.""",,,,,,,,,
Focus Paragraph Detection for Online Zero-Effort Queries: Lessons learned from Eye-Tracking Data,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022138,short,no,gender distribution,"""... (2 female... """,,,,,,,,,
Understanding the Interpretability of Search Result Summaries,SIGIR19,https://dl.acm.org/doi/proceedings/10.1145/3331184,short,no,gender distribution,"""... (20 are female)... """,,,,,,,,,
Privacy Nudging in Search: Investigating Potential Impacts,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298952,short,no,gender distribution,"""... of which 29 were females and 11 were male.""",,,,,,,,,
Exploring Language Style in Chatbots to Increase Perceived Product Value and User Engagement,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298956,short,no,gender distribution,"""... (111 female, 58 male)... """,,,,,,,,,
Stimulating Photo Curation on Smartphones,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298947,short,no,gender distribution,"""Ten people participated (7 women)... """,,,,,,,,,
Clarifying False Memories in Voice-based Search,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298961,short,no,gender distribution,"""... 7 were male and 5 were female... """,,,,,,,,,
Argument Search: Assessing Argument Relevance,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331327,short,no,gender distribution,"""... (31 male, 9 female... """,,,,,,,,,
Immersive Search: Using Virtual Reality to Examine How a Third Dimension Impacts the Searching Process,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401303,short,no,gender distribution,"""... (22 female)... """,,,,,,,,,
The Role of Word-Eye-Fixations for Query Term Prediction,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378010,short,no,gender distribution,"""... 16 were female... """,,,,,,,,,
Visually Linked Keywords to Support Exploratory Browsing,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446037,short,no,gender distribution,"""... 40% identified as female; the rest male.""",,,,,,,,,
The Role of Domain Knowledge in Search as Learning,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377989,short,no,gender distribution,"""There were more participants who identified as female than male... """,,,,,,,,,
Telling How to Narrow it Down: Browsing Path Recommendation for Exploratory Search,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022155,short,no,gender distribution,"""Four participants were male and eight female.""",,,,,,,,,
Too Much Serendipity': The Tension between Information Seeking and Encountering at the Library Shelves,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022132,short,no,gender distribution,"""... (four female, one male)... """,,,,,,,,,
Strategies for Finding and Evaluating Information about Personal Finance Topics: The Role of Government Information,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176883,short,no,gender distribution,"""... consisted of 31 females and 13 males.""",,,,,,,,,
Lessons Learned from Users Reading Highlighted Abstracts in a Digital Library,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298950,short,no,gender distribution,"""Sixteen of the remaining participants were female and nine male.""",,,,,,,,,
Starting Conversations with Search Engines - Interfaces that Elicit Natural Language Queries,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446035,short,no,gender distribution,"""... (57 male, 80 female... """,,,,,,,,,
Supporting Information Task Accomplishment: Helpful Systems and Their Features,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176875,short,no,gender distribution,"""... (20 female, 12 male)... """,,,,,,,,,
Developing Evaluation Metrics for Instant Search Using Mixed Methods Methods,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331293,short,no,gender distribution,"""... 5 females and 9 males.""",,,,,,,,,
QWERTY: The Effects of Typing on Web Search Behavior,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176872,short,no,gender distribution,"""... (18 males and 18 females)... """,,,,,,,,,
Prediction of Good Abandonment Behavior in Mobile Search,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378007,short,no,gender distribution,"""... 40 were female... """,,,,,,,,,
Understanding and Predicting Usefulness Judgment in Web Search,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080750,short,no,gender distribution,"""22 participants are female... """,,,,,,,,,
Perceptions of the Effect of Fragmented Attention on Mobile Web Search Tasks,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022136,short,no,gender distribution,""".. of whom 10 were male... """,,,,,,,,,
ArTest: The First Test Collection for Arabic Web Search with Relevance Rationales,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401223,short,no,gender distribution,"""... (4 males and 12 females)... """,,,,,,,,,
"Column Major Pattern: How Users Process Spatially Fixed Items on Large, Tiled Displays",CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176870,short,no,gender distribution,"""There were 11 female participants... """,,,,,,,,,
Dancing with the AI Devil: Investigating the Partnership Between Lawyers and AI,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378014,short,no,gender distribution,"""... (2 women, 7 men)... """,,,,,,,,,
Generating Tasks for Study of Struggling Search,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298949,short,no,gender distribution,"""... (i.e., 5 female and 5 male... """,,,,,,,,,
I Can and So I Search More: Effects Of Memory Span On Search Behavior,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022148,short,no,gender distribution,"""... (16 females... """,,,,,,,,,
Towards Designing Better Session Search Evaluation Metrics,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210097,short,no,gender distribution,"""24 participants were female... """,,,,,,,,,
Toward Voice Query Clarification,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210160,short,no,gender distribution,"""... 9 were male and 5 female.""",,,,,,,,,
Manipulating the Perception of Credibility in Refugee Related Social Media Posts,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022137,short,no,gender distribution,"""... (55 female... """,,,,,,,,,
The Role of Cognitive Abilities and Time Spent on Texts and Videos in a Multimodal Searching as Learning Task,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3378001,short,no,gender distribution,"""... (96 females... """,,,,,,,,,
A Two-Stage Model for User's Examination Behavior in Mobile Search,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176891,short,no,gender distribution,"""20 of them are female and 23 are male.""",,,,,,,,,
Addressing Vocabulary Gap in E-commerce Search,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331323,short,no,tag,"For example, the query “ladies pregnancy dress” expresses the same need as “women maternity gown”.",,,,,,,,,
Extractive Snippet Generation for Arguments,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401186,short,no,tag,"""Outlawing abortion is taking away a human right given to women.""",,,,,,,,,
Technology Assisted Reviews: Finding the Last Few Relevant Documents by Asking Yes/No Questions to Reviewers,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210102,short,no,tag,"""16 and 18 in young Austrian women""",,,,,,,,,
WikiPassageQA: A Benchmark Collection for Research on Non-factoid Answer Passage Retrieval,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210118,short,no,tag,"""... 50 reserved selected seats for women.""",,,,,,,,,
Cross-Graph Attention Enhanced Multi-Modal Correlation Learning for Fine-Grained Image-Text Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3463031,short,no,tag,"""Woman in a white dress standing with a tennis racket and two people in green behind her.""",,,,,,,,,
Towards Better Support for Exploratory Search through an Investigation of Notes-to-self and Notes-to-share,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331309,short,no,tag,"""Women in Computing"" as a search task",,,,,,,,,
A Collection for Detecting Triggers of Sentiment Spikes,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080715,short,no,tag,"""birthday happy beautiful women inspirational""",,,,,,,,,
Video Question Answering via Attribute-Augmented Attention Network Learning,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080655,short,no,tag,"""What is a woman boiling in a pot of water?""",,,,,,,,,
Characterizing Question Facets for Complex Answer Retrieval,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210135,short,no,tag,"""Which female characters are in the same room as Homer in Act III Scene I?""",,,,,,,,,
Subjective Search Intent Predictions using Customer Reviews,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377987,short,no,tag,"""flannel pajamas for men""",,,,,,,,,
Modeling Transferable Topics for Cross-Target Stance Detection,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331367,short,no,tag,"""All humans, male and female, should have equal political, economic and social rights.""",,,,,,,,,
A Taxonomy of Queries for E-commerce Search,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210152,short,no,tag,"""women's shoes""",,,,,,,,,
Evaluation of Cross Domain Text Summarization,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401285,short,no,tag,"""china takes asian women's volleyball crown""",,,,,,,,,
Training Mixed-Objective Pointing Decoders for Block-Level Optimization in Search Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401236,short,no,tag,"""how to treat thyroid problems in men?""",,,,,,,,,
Symmetric Regularization based BERT for Pair-wise Semantic Reasoning,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401309,short,no,tag,"""a woman is sleeping""",,,,,,,,,
Categorization of Known-Item Search Terms in a TV Archive,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3022143,short,no,tag,"""The clip shows to men walking arund the city Drammen... """,,,,,,,,,
Explaining Controversy on Social Media via Stance Summarization,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210143,short,no,tag,"""We know that it's not okay that for 40 yrs politicians have denied a woman coverage of abortion just because she's poor... """,,,,,,,,,
Term Relevance Feedback for Contextual Named Entity Retrieval,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176886,short,no,tag,"""... the trial of a Virginia woman who provided helpful testimony... """,,,,,,,,,
Investigating Everyday Information Behavior of Using Ambient Displays: A Case of Indoor Air Quality Monitors,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176880,short,no,tag,"""As an active woman, concerned by the threats of downtown NY pollution... """,,,,,,,,,
Automatically Extracting High-Quality Negative Examples for Answer Selection in Question Answering,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080645,short,no,tag,"""... transformed the younger daughter of a provincial English grocer into the greatest woman political leader since Catherine the Great.""",,,,,,,,,
LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462981,short,no,tag,"""What color outfit is the woman wearing?""",,,,,,,,,
"Computational Surprise, Perceptual Surprise, and Personal Background in Text Understanding",CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298963,short,no,tag,"""Women's Health""",,,,,,,,,
Training Effective Neural CLIR by Bridging the Translation Gap,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401035,full,N/A,,"{ cha, han, ang, nge, gem, ement, men, ent }",,,,,,,,,
A Study of Defensive Methods to Protect Visual Recommendation Against Adversarial Manipulation of Images,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462848,full,no,tag,"""Amazon Men"" and ""Amazon Women""",,,,,,,,"""Amazon Women"" and ""Amazon Men"" as two separate datasets used, not non-binary",
Hate Speech Detection is Not as Easy as You May Think: A Closer Look at Model Validation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331262,full,no,tag,"""Multilingual detection of hate speech against immigrants and women in Twitter""",,,,,,,,,
Content Recommendation for Viral Social Influence,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080788,full,applied,vectorized / grouped,""" With k = 3, the selected attributes are {“MODA”, “La vie et l’amour”, “Blog for Men”}.""",,,,,,,,,
Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462960,full,no,demographic data,"""... dataset consists of 344 chemical compund graphs that report the carcinogenicity for male and female rats.""",,,,,,,,,
Computational Social Indicators: A Case Study of Chinese University Ranking,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080773,full,no,demographic data,"""male-female ratio""",,,,,,,,,
Streaming Ranking Based Recommender Systems,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210016,full,no,contextualize argument,"""A very obvious example [of interest drift] is that the preferences of a female who just became a mother will change a lot compared with her previous interests.""",,,,,,,,,
GAME: Learning Graphical and Attentive Multi-view Embeddings for Occasional Group Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401064,full,no,contextualize argument,"""For instance, the genre of a movie is highly possible to be “cartoon” if the movie is attractive to children or “action” if a plenty of young men are attracted.""",,,,,,,,,
CTRec: A Long-Short Demands Evolution Model for Continuous-Time Recommendation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331199,full,no,contextualize argument,"""... e.g., the makeup products adopter is more lkely a women who maybe somewhat less interested in electronic products.""",,,,,,,,,
Humor Detection in Product Question Answering Systems,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401077,full,no,contextualize argument,"""For example, the non-humorous question “Is this stuff safe to
spray directly on your skin?” has high incongruity with its peculiar
product ‘Pheromones for man — attract women"".",,,,,,,,,
Jointly Learning Word Embeddings and Latent Topics,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080806,full,no,contextualize argument,"""... a notable example being vec(“man”) - vec(“king”) ≈ vec(“woman”)
- vec(“queen”).""",,,,,,,,,
Switching Languages in Online Searching: A Qualitative Study of Web Users' Code-Switching Search Behaviors,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176396,full,no,gender distribution,"""Six of them were female... """,,,,,,,,,
Exploration or Fact-Finding: Inferring User's Search Activity Just in Time,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020180,full,no,gender distribution,"""... (13 men and 6 women)... """,,,,,,,,,
Conversational Agents for Recipe Recommendation,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377967,full,no,gender distribution,"""13 participants identified as male, 15 as female... """,,,,,,,,,
The Effect of Nudges and Boosts on Browsing Privacy in a Naturalistic Environment,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446014,full,no,gender distribution,"""70 of the participants identified as male... """,,,,,,,,,
"Measuring Learning During Search: Differences in Interactions, Eye-Gaze, and Semantic Similarity to Expert Knowledge",CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298926,full,no,gender distribution,"""... (16 females... """,,,,,,,,,
Intercomprehension in Retrieval: User Perspectives on Six Related Scarce Resource Languages,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377954,full,no,gender distribution,"""... (13 male and 11 female)... """,,,,,,,,,
The Cortical Activity of Graded Relevance,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401106,full,no,gender distribution,"""... 14 females and 9 males... """,,,,,,,,,
SearchGazer: Webcam Eye Tracking for Remote Studies of Web Search,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020170,full,no,gender distribution,"""The final population consisted of 36 participants
(14 female, 22 male).""",,,,,,,,,
An Intent Taxonomy for Questions Asked in Web Search,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446027,full,no,gender distribution,"""... (one male and four female).""",,,,,,,,,
An Interface for Supporting Asynchronous Multi-Level Collaborative Information Retrieval,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020172,full,no,gender distribution,"""8 females and 12 males... """,,,,,,,,,
Investigating User Behavior in Legal Case Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462876,full,no,gender distribution,"""... (11 males, 34 females)... """,,,,,,,,,
Expressions of Style in Information Seeking Conversation with an Agent,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401127,full,no,gender distribution,"""... (11 women, 13 men)... """,,,,,,,,,
Cascade or Recency: Constructing Better Evaluation Metrics for Session Search,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401163,full,no,gender distribution,"""... 13 females and 17 males... """,,,,,,,,,
What Snippet Size is Needed in Mobile Web Search?,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020173,full,no,gender distribution,"""... 24 participants (13 male)... """,,,,,,,,,
Characterizing and Supporting Question Answering in Human-to-Human Communication,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210046,full,no,gender distribution,"""72% of the repondents were male... """,,,,,,,,,
"Interplay of Documents' Readability, Comprehension and Consumer Health Search Performance Across Query Terminology",CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298927,full,no,gender distribution,"""... (25 females; 15 males)... """,,,,,,,,,
Effects of Past Interactions on User Experience with Recommended Documents,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377977,full,no,gender distribution,"""29% of the remaining participants were female.""",,,,,,,,,
Health Cards for Consumer Health Search,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331194,full,no,gender distribution,"""... 27 females and 21 males... """,,,,,,,,,
Exploiting Food Choice Biases for Healthier Recipe Recommendation,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080826,full,no,gender distribution,"""... (64.5% male)... """,,,,,,,,,
Calendar-Aware Proactive Email Recommendation,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210001,full,no,gender distribution,"""... 63.4% are male, 35.2% female... """,,,,,,,,,
"Juggling with Information Sources, Task Type, and Information Quality",CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176390,full,no,gender distribution,"""... 26 males and 27 females.""",,,,,,,,,
Why do Users Issue Good Queries?: Neural Correlates of Term Specificity,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331243,full,no,gender distribution,"""... 8 were female and 7 male... """,,,,,,,,,
User Perceptions of an Intelligent Personal Assistant's Personality: The Role of Interaction Context,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446018,full,no,gender distribution,"""Female participants comprised 64%... """,,,,,,,,,
Improving Exploratory Search Experience through Hierarchical Knowledge Graphs,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080829,full,no,gender distribution,"""... thirteen female... """,,,,,,,,,
Investigating Examination Behavior of Image Search Users,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080799,full,no,gender distribution,"""... (female=16, male=24)... """,,,,,,,,,
Manoeuvres in the Dark: Design Implications of the Physical Mechanics of Library Shelf Browsing,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020179,full,no,gender distribution,"""16 participants were male, 15 female.""",,,,,,,,,
Understanding and Evaluating User Satisfaction with Music Discovery,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210049,full,no,gender distribution,"""... 5 females and 5 males.""",,,,,,,,,
Modelling Information Needs in Collaborative Search Conversations,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080787,full,no,gender distribution,"""... 30 were female and 38 were male.""",,,,,,,,,
Embedding Search into a Conversational Platform to Support Collaborative Search,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298928,full,no,gender distribution,"""... (44 female and 10 male).""",,,,,,,,,
A Think-Aloud Study to Understand Factors Affecting Online Health Search,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377961,full,no,gender distribution,"""... (7 male, 9 female)... """,,,,,,,,,
Here and Now: Reality-Based Information Retrieval: Perspective Paper,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176384,full,no,gender distribution,"""... (three male, one female... """,,,,,,,,,
Exploring Gaze-Based Prediction Strategies for Preference Detection in Dynamic Interface Elements,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446013,full,no,gender distribution,"""... (36 female... """,,,,,,,,,
Informing the Design of Spoken Conversational Search: Perspective Paper,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176387,full,no,gender distribution,"""Fifteen participants were female and eleven were male.""",,,,,,,,,
Take Me Out: Space and Place in Library Interactions,CHIIR19,https://dl.acm.org/doi/10.1145/3295750.3298935,full,no,gender distribution,"""... seven female and five male students.""",,,,,,,,,
Generating Images Instead of Retrieving Them: Relevance Feedback on Generative Adversarial Networks,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401129,full,no,gender distribution,"""... 19 were male and 10 were female.""",,,,,,,,,
How Can We Better Support Users with Non-Uniform Information Access in Collaborative Information Retrieval?,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020171,full,no,gender distribution,"""There were 9 females and 11 males.""",,,,,,,,,
"Investigating the Influence of Ads on User Search Performance, Behaviour, and Experience during Information Seeking",CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446024,full,no,gender distribution,"""... 14 females... """,,,,,,,,,
Engaging the Abilities of Participants with Intellectual Disabilityin IIR Research,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377972,full,no,gender distribution,"""... with 8 adults, 4 females... """,,,,,,,,,
Files of a Feather Flock Together? Measuring and Modeling How Users Perceive File Similarity in Cloud Storage,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462845,full,no,gender distribution,"""... 54.0% were female, 40.0% were male, and 6.0% were non-binary.""",,,,,,,,,
Improving Exploration of Topic Hierarchies: Comparative Testing of Simplified Library of Congress Subject Heading Structures,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176385,full,no,gender distribution,"""... 60% are female... """,,,,,,,,,
OrgBox: A Knowledge Representation Tool to Support Complex Search Tasks,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446029,full,no,gender distribution,"""... (26 female).""",,,,,,,,,
"A Study of Snippet Length and Informativeness: Behaviour, Performance and User Experience",SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080824,full,no,gender distribution,"""... 28 were male, with 25 female.""",,,,,,,,,
A Study of Immediate Requery Behavior in Search,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176400,full,no,gender distribution,"""... and 26 were female participants.""",,,,,,,,,
Standing in Your Shoes: External Assessments for Personalized Recommender Systems,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462916,full,no,gender distribution,"""... (8 are female)... """,,,,,,,,,
Prototype-guided Attribute-wise Interpretable Scheme for Clothing Matching,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331245,full,no,gender distribution,"""... 6 males and 14 females.""",,,,,,,,,
Between Clicks and Satisfaction: Study on Multi-Phase User Preferences and Satisfaction for Online News Reading,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210007,full,no,gender distribution,"""... (18 were female)... """,,,,,,,,,
User Behaviour and Task Characteristics: A Field Study of Daily Information Behaviour,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020188,full,no,gender distribution,"""... 13 males and 10 females... """,,,,,,,,,
The Lifetime of Email Messages: A Large-Scale Analysis of Email Revisitation,CHIIR18,https://dl.acm.org/doi/10.1145/3176349.3176398,full,no,gender distribution,"""74% of the respondents were male... """,,,,,,,,,
Models Versus Satisfaction: Towards a Better Understanding of Evaluation Metrics,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401162,full,no,gender distribution,"""... 13 females and 17 males... """,,,,,,,,,
Engaged or Frustrated?: Disambiguating Emotional State in Search,SIGIR17,https://dl.acm.org/doi/10.1145/3077136.3080818,full,no,gender distribution,"""... and most were female.""",,,,,,,,,
How Well do Offline and Online Evaluation Metrics Measure User Satisfaction in Web Image Search?,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210059,full,no,gender distribution,"""... (14 female and 22 male)... """,,,,,,,,,
Identifying Sub-events and Summarizing Disaster-Related Information from Microblogs,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210030,full,no,gender distribution,"""... (15 male and 5 female candidates)... """,,,,,,,,,
Human Behavior Inspired Machine Reading Comprehension,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331231,full,no,gender distribution,"""There are 21 males and 11 females... """,,,,,,,,,
I've Got All My Readers With Me: A Model of Reading as a Social Activity,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446022,full,no,gender distribution,"""... 8 male and 6 female)... """,,,,,,,,,
Identifying and Predicting the States of Complex Search Tasks,CHIIR20,https://dl.acm.org/doi/10.1145/3343413.3377976,full,no,tag,"""... and between 1994 and 2000 women from India won two Miss Universe competitions... """,,,,,,,,,
Can The Crowd Identify Misinformation Objectively?: The Effects of Judgment Scale and Assessor's Background,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401112,full,no,tag,"""In an athletics team, females are four times more likely to win a medal than males.""",,,,,,,,,
User Attention-guided Multimodal Dialog Systems,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331226,full,no,tag,"""I am a 35-year-old man.""",,,,,,,,,
Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401151,full,no,tag,"""a clip of men and women dancing at a reception""",,,,,,,,,
Jointly Modeling Relevance and Sensitivity for Search Among Sensitive Content,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331256,full,no,tag,"""Female Urogenital Diseases and Pregnancy Complications""",,,,,,,,,
CROSS: Cross-platform Recommendation for Social E-Commerce,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331191,full,no,tag,"""women's clothes""",,,,,,,,,
Privacy Protection in Deep Multi-modal Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462837,full,no,tag,"""female, people, water, sky, sunset, blue""",,,,,,,,,
Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identification,CHIIR21,https://dl.acm.org/doi/10.1145/3406522.3446021,full,no,tag,"""The woman looked like Annie Clark.""",,,,,,,,,
User-Centric Path Reasoning towards Explainable Recommendation,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462847,full,no,tag,"""Men in Black""",,,,,,,,,
EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331193,full,no,tag,"""I know you're male, I'm female.""",,,,,,,,,
Semi-Supervised Variational Reasoning for Medical Dialogue Generation,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462921,full,no,tag,"""Is it allergic rhinitis (female, 19 years old)?""",,,,,,,,,
MVIN: Learning Multiview Items for Recommendation,SIGIR20,https://dl.acm.org/doi/10.1145/3397271.3401126,full,no,tag,"""Men in Black""",,,,,,,,,
Deconfounded Video Moment Retrieval with Causal Intervention,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462823,full,no,tag,"""An old men is playing the piano in front of a crowd""",,,,,,,,,
Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos,SIGIR19,https://dl.acm.org/doi/10.1145/3331184.3331235,full,no,tag,"""The female athlete jumped over the pole and wave at everyone.""",,,,,,,,,
The Rise of Guardians: Fact-checking URL Recommendation to Combat Fake News,SIGIR18,https://dl.acm.org/doi/10.1145/3209978.3210037,full,no,tag,used in graphic,,,,,,,,,
Glider: A Reinforcement Learning Approach to Extract UI Scripts from Websites,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462905,full,no,tag,"""Find women shoes""",,,,,,,,,
GilBERT: Generative Vision-Language Pre-Training for Image-Text Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462838,full,no,tag,"""Men's Women's Casual Sport Shoes""",,,,,,,,,
Structure-Aware Visualization of Text Corpora,CHIIR17,https://dl.acm.org/doi/10.1145/3020165.3020182,full,no,tag,"""Examples for characteristic latent topics for a movie dataset used for our evaluation (cf. Section 4) were “vampire blood coffin” for the category “Horror” and “army soldiers men” for category “War”.""",,,,,,,,,
Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462911,full,no,tag,"""clothing shoe jewelry men big tall active athletic sock""",,,,,,,,,
Dynamic Modality Interaction Modeling for Image-Text Retrieval,SIGIR21,https://dl.acm.org/doi/10.1145/3404835.3462829,full,no,tag,"""A woman in blue looks in a black leather bag... """,,,,,,,,,
Controlling Popularity Bias in Learning-to-Rank Recommendation,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109912,short,applied,contextualize argument,"""One example of a two-set fairness is in educational recommender systems where the system wants to keep a fair balance between items recommended to females versus those recommended to males.""",,,,,,,,,
Defining and Supporting Narrative-driven Recommendation,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109893,short,no,contextualize argument,"""Have you any other manly books for manly men such as I?” (ID-B24040).""",,,,,,,,,
Ghosting: contextualized inline query completion in large scale retail search,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3346995,short,no,tag,"""dance clothes for women""",,,,,,,,,
Decomposing fit semantics for product size recommendation in metric spaces,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240398,short,no,tag,"""women's vintage clothing""",,,,,,,,,
Impact of item consumption on assessment of recommendations in user studies,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240375,short,no,gender distribution,"""We conducted a controlled experiment with 40 participants (22 female)... """,,,,,,,,,
The influence of personal values on music taste: towards value-based music recommendations,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347021,short,no,gender distribution,"""In the population, we had 33% female participants."" ",,,,,,,,,
Audio-visual encoding of multimedia content for enhancing movie recommendations,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240407,short,no,gender distribution,"""... (54 male, 20 female, mean age... """,,,,,,,,,
Explainable Recommendation for Repeat Consumption,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412230,short,no,gender distribution,"""... and 326 were female.""",,,,,,,,,
Exploring the Semantic Gap for Movie Recommendations,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109908,short,no,gender distribution,"""... (63% men, 37% women... """,,,,,,,,,
User Preferences for Hybrid Explanations,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109915,short,no,gender distribution,"""... and 42% were male.""",,,,,,,,,
Providing explanations for recommendations in reciprocal environments,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240362,full,yes,,,users,no,male / female,no,self-identification,audit system behavior / user study or survey,no,"Results from the operational online-dating platform naturally reflect the real-world impact of both explanation methods, whereas in the simulated environment one receives detailed and explicit feedback from the users, which otherwise would be impractical to gather in an active online-dating platform.",
ImRec: Learning Reciprocal Preferences Using Images,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3411476,full,yes,,,users,no,male / female,no,self-identification,gender personalization,no,"A recommendation algorithm for a dating site that is said to be adaptable based on orientation..? Assumes heterosexual pairings, edge case, no distinction between user-item, data is from Pairs dating site, so vendor or self-id?",
LORE: a large-scale offer recommendation engine with eligibility and capacity constraints,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347027,full,yes,,,subject,no,male / female,no,annotators,gender interest personalization,no,emails sent out of men's merchandise and women's merchandise offers,
"Tops, Bottoms, and Shoes: Building Capsule Wardrobes via Cross-Attention Tensor Network",RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474258,full,no,contextualize argument,"""Concrete suggestions for women, such as ""the hoods may be made of satin to match the lining and frill of the jacket, but should be lined with fine white cashmere"", were given as specific dressing instructions.""",,,,,,,,,
“Who doesn’t like dinosaurs?” Finding and Eliciting Richer Preferences for Recommendation,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412267,full,no,gender distribution,"""We recruited 518 (63% male, 37% female... """,,,,,,,,,
Effective User Interface Designs to Increase Energy-efficient Behavior in a Rasch-based Energy Recommender System,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109902,full,no,gender distribution,"""The sample comprised 193 female users... """,,,,,,,,,
The Magic Barrier Revisited: Accessing Natural Limitations of Recommender Assessment,RecSys17,https://dl.acm.org/doi/10.1145/3109859.3109898,full,no,gender distribution,"""... 57% females... """,,,,,,,,,
Generation meets recommendation: proposing novel items for groups of users,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240357,full,no,gender distribution,"""... (74 females... """,,,,,,,,,
In-Store Augmented Reality-Enabled Product Comparison and Recommendation,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412266,full,no,gender distribution,"""A total of 10 participants (4 female... """,,,,,,,,,
Relaxed softmax for PU learning,RecSys19,https://dl.acm.org/doi/10.1145/3298689.3347034,full,no,tag,"""Semantic analogies test the robustness of word embeddings to transformations such as ""man"" to ""woman""... """,,,,,,,,,
Quality-aware neural complementary item recommendation,RecSys18,https://dl.acm.org/doi/10.1145/3240323.3240368,full,no,tag,"""... such as splitting Clothing into Men's, Women's, Boys, Girls... """,,,,,,,,,
Evaluating the Robustness of Off-Policy Evaluation,RecSys21,https://dl.acm.org/doi/10.1145/3460231.3474245,full,no,tag,"""There are three campaigns, ""ALL"", ""Men"", and ""Women"". We... sub-sampled data from the ""ALL"" campaign.""",,,,,,,,,
Content-Collaborative Disentanglement Representation Learning for Enhanced Recommendation,RecSys20,https://dl.acm.org/doi/10.1145/3383313.3412239,full,no,tag,"""... separates items by user-oriented information, e.g., items used by male (left bottom) and female (right top).""",,,,,,,,,
Fairness and Transparency in Recommendation: The Users’ Perspective,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456835,short,no,contextualize argument,"""Most of the proposed methods try to ensure parity in either of these factors among all user groups (e.g., women vs. men)... """,,,,,,,,,
More Than Accuracy: Towards Trustworthy Machine Learning Interfaces for Object Recognition,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394873,short,no,gender distribution,"""... (13 male, two female)... """,,,,,,,,,
Personalized Gait-based Authentication Using UWB Wearable Device,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320473,short,no,gender distribution,"""... eight males and two females... """,,,,,,,,,
Modeling Behavior Patterns with an Unfamiliar Voice User Interface,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320475,short,no,gender distribution,"""... 25 males and 25 females... """,,,,,,,,,
On the Accuracy of Eye Gaze-driven Classifiers for Predicting Image Content Familiarity in Graphical Passwords,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320474,short,no,gender distribution,"""... (13 females)... """,,,,,,,,,
Eudaimonic Modeling of Moviegoers,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209249,short,no,gender distribution,"""... 29 females).""",,,,,,,,,
Human Strategic Steering Improves Performance of Interactive Optimization,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394883,short,no,gender distribution,"""... and there were 12 women.""",,,,,,,,,
An Exploratory Study on Techniques for Quantitative Assessment of Stroke Rehabilitation Exercises,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394872,short,no,gender distribution,"""Fifteen post-stroke patients (2 females)... """,,,,,,,,,
Personalisation in Cyber-Physical-Social Systems: A Multi-stakeholder aware Recommendation and Guidance,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456847,short,no,tag,"""... (Women's Lives, Contemporary Style & Fashion, Water, Women Artists & Famous Women, Warfare... """,,,,,,,,,
Towards a User Integration Framework for Personal Health Decision Support and Recommender Systems,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456816,full,no,contextualize argument,"""For example, in a system that supports men in decision making regarding prostate cancer screening... """,,,,,,,,,
FairMatch: A Graph-based Approach for Improving Aggregate Diversity in Recommender Systems,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394860,full,no,future work / footnote / citations,"""... to each group of users based on sensitive attributes (e.g. men and women).""",,,,,,,,,
Modeling Cognitive Status through Automatic Scoring of a Digital Version of the Clock Drawing Test,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320452,full,no,gender distribution,"""... (3 female, 8 male)... """,,,,,,,,,
Intelligent Shifting Cues: Increasing the Awareness of Multi-Device Interaction Opportunities,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456839,full,no,gender distribution,"""... (24 female, 33 male and 1 prefers not to say)... """,,,,,,,,,
Real-Time Public Transport Navigation on Smartwatches: A Comparison with a Smartphone-based Solution,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099053,full,no,gender distribution,"""... (5 females and 11 males)... """,,,,,,,,,
"RouteMe: A Mobile Recommender System for Personalized, Multi-Modal Route Planning",UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079680,full,no,gender distribution,"""... (4 females and 13 males).""",,,,,,,,,
Personalized Recommendations for Music Genre Exploration,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320455,full,no,gender distribution,"""... with 78 females and 78 males.""",,,,,,,,,
Assessing Cognitive Test Performance Using Automatic Digital Pen Features Analysis,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456812,full,no,gender distribution,"""... of which half are female.""",,,,,,,,,
Inferring Contextual Preferences Using Deep Auto-Encoding,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079666,full,no,gender distribution,"""... (53 male and 37 female)... """,,,,,,,,,
Are All Rejected Recommendations Equally Bad?: Towards Analysing Rejected Recommendations,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320448,full,no,gender distribution,"""... 53 of them female, and 94 male... """,,,,,,,,,
Effects and Ways of Tailored Gamification in Software-Based Training in Cognitive Rehabilitation,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456828,full,no,gender distribution,"""... (f (female)=29; m (male)=38... """,,,,,,,,,
WalkWithMe: Personalized Goal Setting and Coaching for Walking in People with Multiple Sclerosis,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320459,full,no,gender distribution,"""All participants were female... """,,,,,,,,,
What's in a User? Towards Personalising Transparency for Music Recommender Interfaces,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394844,full,no,gender distribution,"""... (9 female).""",,,,,,,,,
Enhancing Student Models in Game-based Learning with Facial Expression Recognition,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079686,full,no,gender distribution,"""... of which 17 (51.5%) were female.""",,,,,,,,,
Studying Personalized Just-in-time Auditory Breathing Guides and Potential Safety Implications during Simulated Driving,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394854,full,no,gender distribution,"""... there were 14 females and 12 males... """,,,,,,,,,
The Potential of Wrist-Worn Wearables for Driver Drowsiness Detection: A Feasibility Analysis,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394852,full,no,gender distribution,"""... (7 female, 8 male... """,,,,,,,,,
Gaze-Enhanced Student Modeling for Game-based Learning,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209238,full,no,gender distribution,"""... (68%) were female.""",,,,,,,,,
Progression Trajectory-Based Student Modeling for Novice Block-Based Programming,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456833,full,no,gender distribution,"""... with 74% reporting as male and 26% as female.""",,,,,,,,,
Effects of Proactive Dialogue Strategies on Human-Computer Trust,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394840,full,no,gender distribution,"""... (50 % female)... """,,,,,,,,,
Justifying Recommendations through Aspect-based Sentiment Analysis of Users Reviews,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320457,full,no,gender distribution,""" ... 73.6% male)... """,,,,,,,,,
Towards Social Choice-based Explanations in Group Recommender Systems,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320437,full,no,gender distribution,"""... (male: 54.81%, female: 45.19%)... """,,,,,,,,,
Kindness is Contagious: Study into Exploring Engagement and Adapting Persuasive Games for Wellbeing,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209233,full,no,gender distribution,"""... (17 females and 28 males... """,,,,,,,,,
Using Eye Gaze Data and Visual Activities to Infer Human Cognitive Styles: Method and Feasibility Studies,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079690,full,no,gender distribution,"""... (9 females)... """,,,,,,,,,
Investigating the Impact of Personality and Cognitive Efficiency on the Selection of Exercises for Learners,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079674,full,no,gender distribution,"""... 94 females... """,,,,,,,,,
Inside Out: Exploring the Emotional Side of Search Engines in the Classroom,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394847,full,no,gender distribution,"""... uniformly distributed among males and females... """,,,,,,,,,
NewsViz: Depicting and Controlling Preference Profiles Using Interactive Treemaps in News Recommender Systems,UMAP20,https://dl.acm.org/doi/10.1145/3340631.3394869,full,no,gender distribution,"""... (31 female)... """,,,,,,,,,
Impact of English Reading Comprehension Abilities on Processing Magazine Style Narrative Visualizations and Implications for Personalization,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320447,full,no,gender distribution,"""... (15 females)... """,,,,,,,,,
Let's Dance: How to Build a User Model for Dance Students Using Wearable Technology,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079673,full,no,gender distribution,"""... 5 females and 5 males... """,,,,,,,,,
Probabilistic Perspectives on Collecting Human Uncertainty in Predictive Data Mining,UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079675,full,no,gender distribution,"""... 57% females and 43% males... """,,,,,,,,,
Learning to Trust: Understanding Editorial Authority and Trust in Recommender Systems for Education,UMAP21,https://dl.acm.org/doi/10.1145/3450613.3456811,full,no,gender distribution,#Male/Female,,,,,,,,,
"""An Unscented Hound for Working Memory"" and the Cognitive Adaptation of User Interfaces",UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320443,full,no,gender distribution,"""... (7 females)... """,,,,,,,,,
"""Out of the Fr-Eye-ing Pan"": Towards Gaze-Based Models of Attention during Learning with Technology in the Classroom",UMAP17,https://dl.acm.org/doi/10.1145/3079628.3079669,full,no,gender distribution,"""... (41% male)... """,,,,,,,,,
Easy to Please: Separating User Experience from Choice Satisfaction,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209222,full,no,gender distribution,"""... were 45% male.""",,,,,,,,,
How to Use Social Relationships in Group Recommenders: Empirical Evidence,UMAP18,https://dl.acm.org/doi/10.1145/3209219.3209226,full,no,gender distribution,"""... 75 male, 75 female... """,,,,,,,,,
Evaluating Visual Explanations for Similarity-Based Recommendations: User Perception and Performance,UMAP19,https://dl.acm.org/doi/10.1145/3320435.3320465,full,no,gender distribution,"""A total of 15 (6 female) participants... """,,,,,,,,,
Designing with AI for Digital Marketing,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397600,LBR,no,contextualize argument,"""Additionally, the finding that credibility is tied to a shorter number of syllables was established with limited cohort of exclusively young men in the military.""",,,,,,,,,
Automatically Adjusting Computer Screen,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324980,LBR,no,contextualize argument,"""... and [35] showed that providing ergonomic counseling can reduce WRNP among female computer users.""",,,,,,,,,
"Everybody, More or Less, likes Serendipity",UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099064,LBR,no,gender distribution,"""... 36% are male.""",,,,,,,,,
Do the Urgent Things first! - Detecting Urgency in Spoken Utterances based on Acoustic Features,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397598,LBR,no,gender distribution,"""... 15 female.""",,,,,,,,,
Exer-model: A User Model for Scrutinising Long-term Models of Physical Activity from Multiple Sensors,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3324986,LBR,no,gender distribution,"""... (six women)... """,,,,,,,,,
The Impact of Adaptation Based on Students' Dyslexia Type: An Empirical Evaluation of Students' Satisfaction,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397596,LBR,no,gender distribution,"""All students were female... """,,,,,,,,,
Interactions between Inter- and Intra-Individual Effects on Gaze Behavior,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397595,LBR,no,gender distribution,"""... (one female... """,,,,,,,,,
Argumentation-Based Explanations in Recommender Systems: Conceptual Framework and Empirical Results,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225240,LBR,no,gender distribution,"""... (45 female)... """,,,,,,,,,
Generating Consensus Explanations for Group Recommendations: an exploratory study,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225231,LBR,no,gender distribution,"""... and 20% female.""",,,,,,,,,
Towards Generating Personalized Country Recommendation,UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397601,LBR,no,gender distribution,"""... 27% were female... """,,,,,,,,,
Leveraging Interfaces to Improve Recommendation Diversity,UMAP17*,https://dl.acm.org/doi/10.1145/3099023.3099073,LBR,no,gender distribution,"""... (nine male and three female)... """,,,,,,,,,
"Personality Traits, Speech and Adaptive In-Vehicle Voice Output",UMAP20*,https://dl.acm.org/doi/10.1145/3386392.3397592,LBR,no,gender distribution,"""A total of 47 subjects (19 female)... """,,,,,,,,,
Towards Intelligent Interfaces for Mixed-Focus Collaboration,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225239,LBR,no,gender distribution,"""There were 11 female... """,,,,,,,,,
Stationary vs. Non-stationary Mobile Learning in MOOCs,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225241,LBR,no,gender distribution,"""... 9 women and 27 men.""",,,,,,,,,
Increasing Response Rates to Email Surveys in MOOCs,UMAP18*,https://dl.acm.org/doi/10.1145/3213586.3225247,perspective,no,gender distribution,"""... 68.5% of the participants were male.""",,,,,,,,,
Human-Agent Interaction for Human Space Exploration,UMAP19*,https://dl.acm.org/doi/10.1145/3314183.3323452,perspective,no,contextualize argument,"""... people prefer different types of explanations (e.g., men and women on dating sites)... """,,,,,,,,,