Computer-based personality judgments are more accurate than those made by humans

Summary & key facts

Researchers compared how well computers and humans can judge personality. They used data from 86,220 volunteers who took a 100-item personality questionnaire and looked at people’s Facebook Likes as the computer’s input. Computer predictions based on Likes matched the questionnaire scores better (r = 0.56) than friends’ judgments did (r = 0.49). The computer models also agreed more with each other and predicted real-life outcomes like substance use, political views, and physical health at least as well as human judgments, and for some outcomes even better than people’s own self-ratings. The authors say these results create both opportunities and challenges for testing, marketing, and privacy

Key facts:

• The study used 86,220 volunteers who completed a 100-item personality questionnaire.
• Computer predictions used a person’s Facebook Likes as the digital data source.
• Computer predictions correlated with questionnaire scores at r = 0.56, while friends’ judgments correlated at r = 0.49 (higher r means closer match).
• Computer models showed higher agreement between different computer judges than between human judges.
• Computer judgments had higher external validity for predicting life outcomes such as substance use, political attitudes, and physical health.
• For some life-outcome predictions, computer judgments outperformed the people’s own self-rated personality scores.

Abstract

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.

Topics

Cognitive Abilities and Testing Evolutionary Psychology and Human Behavior Personality Traits and Psychology

Categories

Clinical Psychology Psychology Social Sciences

Tags

Anthropology Cognition Cognitive psychology Neuroscience Personality Personality psychology Psychology Social psychology Sociology Spouse