`Expected most of the results, but some others...surprised me': Personality inference in Image Tagging Services
- 1. Cyprus Center for Algorithmic Transparency, Open University of Cyprus
- 2. Cyprus Center for Algorithmic Transparency, Open University of Cyprus and CYENS Centre of Excellence
Description
Image tagging APIs, offered as Cognitive Services in the movement to democratize AI, have become popular in applications that need to provide a personalized user experience. Developers can easily incorporate these services into their applications; however, little is known concerning their behavior under specific circumstances. We consider how two such services behave when predicting elements of the Big-Five personality traits from users’ profile images. We found that personality traits are not equally represented in the APIs’ output tags, with tags focusing mostly on Extraversion. The inaccurate personality prediction and the lack of vocabulary for the equal representation of all personality traits, could result in unreliable implicit user modeling, resulting in sub-optimal – or even undesirable – user experience in the application.
Notes
Files
iseud_personality__2021.pdf
Files
(185.9 kB)
Name | Size | Download all |
---|---|---|
md5:f31e209d45a94b635cd159c08419513c
|
185.9 kB | Preview Download |