Data and code for project "What makes users click: The effect of news values negativity and surprise in news headlines on selection likelihood"

This project was carried out by Communication Studies students at VU University Amsterdam for the course "Digital Humanities and Social Analytics in Practice".

All data and code are for a scientific purpose. 

Description of the files in the data_and_code_What_makes_users_click_project.zip file:

• original_data
  • upworthy-archive-confirmatory-packages-03.12.2020.csv: original dataset downloaded from The Upworthy Research Archive (https://osf.io/jd64p/)
• cleaned_data
  • notebook_clean_data.ipynb: Python code for cleaning the original data 
  • cleaned_data.csv: cleaned data file 
• sample_data
  • notebook_sample_manual_annotations.ipynb: Python code to draw a sample from the cleaned data file
  • sample_manual_annotations.csv: sample data file
  • inter_annotator_study
    • inter-annotations_and_gold_annotations.csv: file with values of the two annotators and the gold values
    • notebook_inter-annotator_scores_confusion_matrix.ipynb: Python code to calculate inter-annotator scores and create a confusion matrix 
    • inter-annotator_sentiment.csv: input file with values of the two annotators for the label sentiment
    • inter-annotator_emotion.csv: input file with values of the two annotators for the label emotion
  • annotating_sample_data
    • lexicon
      • NRC-Emotion-Lexicon-Wordlevel-v0.92.txt: NRC Emotion Lexicon used
    • notebook_sentiment_emotion_test_set.ipynb: Python code to annotate headlines in sample data file
    • input_sentiment.tsv: input file with gold values for the label sentiment for the headlines in de sample data file
    • input_emotion.tsv: input file with gold values for the label emotion in de sample data file
• final_data
  • notebook_merge_dataframes.ipynb: Python code to merge cleaned data file with output files of the sentiment and emotion analyses
  • final_dataset.csv: final data file
  • annotating_final_data
    • lexicon
      • NRC-Emotion-Lexicon-Wordlevel-v0.92.txt: NRC Emotion Lexicon used
    • notebook_sentiment_emotion_final_annotation.ipynb: Python code to annotate headlines in final data file
    • input_all_headlines.tsv: input file with all headlines of the final data file
  • data_analyses
    • notebook_descriptive_statistics.ipynb: Python code to obtain descriptive statistics
    • multilevel_regression_analysis.R: R code to perform regression analyses