Faculty Sponsor
Necdet Gurkan
Final Abstract for URS Program
Various computational models of first impressions have been developed to uncover the mechanisms driving these judgments. However, the implicit notion of a singular ``human'' often overlooks meaningful individual differences in beliefs, attitudes, and associations, as well as culturally grounded group-level constructs. In this paper, we extend Cultural Consensus Theory (CCT) to estimate culturally shared beliefs about faces by incorporating latent constructs structured around interpretable facial features extracted via computer vision algorithms. We apply our model to a large-scale dataset of people’s first impressions of faces. Our approach reveals a robust mapping between facial features and culturally constructed impressions, allowing us to identify which features are most influential in shaping distinct cultural subgroups. Our research advances the understanding of how cultural and perceptual mechanisms interact in impression formation and offers a novel framework for modeling cultural consensuses in subjective social judgments.
Presentation Type
Visual Presentation
Document Type
Article
2309.09787v2.pdf (5666 kB)
30_cultural_alignment_of_machine_.pdf (261 kB)
matz2019-1.pdf (6457 kB)
Included in
Artificial Intelligence and Robotics Commons, Bioinformatics Commons, Cognitive Psychology Commons, Cognitive Science Commons, Data Science Commons, Experimental Analysis of Behavior Commons, Geometry and Topology Commons, Software Engineering Commons, Theory and Algorithms Commons