English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Research in social psychology has shown that people's biased, subjectivejudgments about another's personality based solely on their appearance are notpredictive of their actual personality traits. But researchers and companiesoften utilize computer vision models to predict similarly subjectivepersonality attributes such as "employability." We seek to determine whetherstate-of-the-art, black box face processing technology can learn human-likeappearance biases. With features extracted with FaceNet, a widely used facerecognition framework, we train a transfer learning model on human subjects'first impressions of personality traits in other faces as measured by socialpsychologists. We find that features extracted with FaceNet can be used topredict human appearance bias scores for deliberately manipulated faces but notfor randomly generated faces scored by humans. Additionally, in contrast towork with human biases in social psychology, the model does not find asignificant signal correlating politicians' vote shares with perceivedcompetence bias. With Local Interpretable Model-Agnostic Explanations (LIME),we provide several explanations for this discrepancy. Our results suggest thatsome signals of appearance bias documented in social psychology are notembedded by the machine learning techniques we investigate. We shed light onthe ways in which appearance bias could be embedded in face processingtechnology and cast further doubt on the practice of predicting subjectivetraits based on appearances.

A Set of Distinct Facial Traits Learned by Machines Is Not Predictive of Appearance Bias in the Wild