Judging others' personalities is an essential skill in successful social living, as personality is a key driver behind people's interactions, behaviors, and emotions. Although accurate personality judgments stem from social-cognitive skills, developments in machine learning show that computer models can also make valid judgments. This study compares the accuracy of human and computer-based personality judgments, using a sample of 86,220 volunteers who completed a 100-item personality questionnaire. We show that (i) computer predictions based on a generic digital footprint (Facebook Likes) are more accurate (r 0.56) than those made by the participants' Facebook friends using a personality questionnaire (r 0.49); (ii) computer models show higher interjudge agreement; and (iii) computer personality judgments have higher external validity when predicting life outcomes such as substance use, political attitudes, and physical health; for some outcomes, they even outperform the self-rated personality scores. Computers outpacing humans in personality judgment presents significant opportunities and challenges in the areas of psychological assessment, marketing, and privacy.
Russian researchers from HSE University and Open University for the Humanities and Economics have demonstrated that artificial intelligence is able to infer people's personality from'selfie' photographs better than human raters do. Conscientiousness emerged to be more easily recognizable than the other four traits. Personality predictions based on female faces appeared to be more reliable than those for male faces. The technology can be used to find the'best matches' in customer service, dating or online tutoring. The article, "Assessing the Big Five personality traits using real-life static facial images," will be published on May 22 in Scientific Reports.
Biel, Joan-Isaac (Ecole Polytecnique Fédérale de Lausanne (EPFL) and Idiap Research Institute) | Aran, Oya (Idiap Research Institute) | Gatica-Perez, Daniel (Ecole Polytecnique Fédérale de Lausanne (EPFL) and Idiap Research Institute)
An increasing interest in understanding human perception in social media has led to the study of the processes of personality self-presentation and impression formation based on user profiles and text blogs. However, despite the popularity of online video, we do not know of any attempt to study personality impressions that go beyond the use of text and still photos. In this paper, we analyze one facet of YouTube as a repository of brief behavioral slices in the form of personal conversational vlogs, which are a unique medium for self-presentation and interpersonal perception. We investigate the use of nonverbal cues as descriptors of vloggers' behavior and find significant associations between automatically extracted nonverbal cues for several personality judgments. As one notable result, audio and visual cues together can be used to predict 34% of the variance of the Extraversion trait of the Big Five model. In addition, we explore the associations between vloggers' personality scores and the level of social attention that their videos received in YouTube. Our study is conducted on a dataset of 442 YouTube vlogs and 2,210 annotations collected using Amazon's Mechanical Turk.
We address the study of interpersonal perception in social conversational video based on multifaceted impressions collected from short video-watching. First, we crowdsourced the annotation of personality, attractiveness, and mood impressions for a dataset of YouTube vloggers, generating a corpora that has potential to develop automatic techniques for vlogger characterization. Then, we provide an analysis of the crowdsourced annotations focusing on the level of agreement among annotators, as well as the interplay between different impressions. Overall, this work provides interesting new insights on vlogger impressions and the use of crowdsourcing to collect behavioral annotations from multimodal data.
This study compares the accuracy of personality judgment a ubiquitous and important social-cognitive activity between computer models and humans. Using several criteria, we show that computers judgments of people's personalities based on their digital footprints are more accurate and valid than judgments made by their close others or acquaintances (friends, family, spouse, colleagues, etc.). Our findings highlight that people's personalities can be predicted automatically andwithout involving human social-cognitive skills.