How smart does your profile image look? Estimating intelligence from social network profile images
Profile images on social networks are users’ opportunity topresent themselves and to affect how others judge them. Weexamine what Facebook images say about users’ perceivedand measured intelligence. 1,122 Facebook users completeda matrices intelligence test and shared their current Facebookprofile i...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Tagungsbericht |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Profile images on social networks are users’ opportunity topresent themselves and to affect how others judge them. Weexamine what Facebook images say about users’ perceivedand measured intelligence. 1,122 Facebook users completeda matrices intelligence test and shared their current Facebookprofile image. Strangers also rated the images for perceivedintelligence. We use automatically extracted imagefeatures to predict both measured and perceived intelligence.Intelligence estimation from images is a difficult task evenfor humans, but experimental results show that human accuracycan be equalled using computing methods. We reportthe image features that predict both measured and perceivedintelligence, and highlight misleading features suchas "smiling” and "wearing glasses” that are correlated withperceived but not measured intelligence. Our results give insightsinto inaccurate stereotyping from profile images andalso have implications for privacy, especially since in mostsocial networks profile images are public by default. |
---|---|
DOI: | 10.1145/3018661.3018663 |