Title |
Computer-based personality judgments are more accurate than those made by humans
|
---|---|
Published in |
Proceedings of the National Academy of Sciences of the United States of America, January 2015
|
DOI | 10.1073/pnas.1418680112 |
Pubmed ID | |
Authors |
Wu Youyou, Michal Kosinski, David Stillwell |
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. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 218 | 18% |
United Kingdom | 75 | 6% |
Spain | 55 | 4% |
Germany | 30 | 2% |
Chile | 29 | 2% |
Canada | 28 | 2% |
France | 24 | 2% |
Switzerland | 24 | 2% |
Netherlands | 20 | 2% |
Other | 249 | 20% |
Unknown | 487 | 39% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 970 | 78% |
Scientists | 213 | 17% |
Science communicators (journalists, bloggers, editors) | 35 | 3% |
Practitioners (doctors, other healthcare professionals) | 21 | 2% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 24 | 1% |
United Kingdom | 15 | <1% |
Germany | 9 | <1% |
Australia | 5 | <1% |
Brazil | 5 | <1% |
Spain | 4 | <1% |
Austria | 3 | <1% |
Finland | 3 | <1% |
Turkey | 2 | <1% |
Other | 26 | 1% |
Unknown | 1731 | 95% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 354 | 19% |
Student > Master | 282 | 15% |
Student > Bachelor | 222 | 12% |
Researcher | 187 | 10% |
Student > Doctoral Student | 100 | 5% |
Other | 371 | 20% |
Unknown | 311 | 17% |
Readers by discipline | Count | As % |
---|---|---|
Psychology | 443 | 24% |
Computer Science | 257 | 14% |
Social Sciences | 171 | 9% |
Business, Management and Accounting | 150 | 8% |
Engineering | 58 | 3% |
Other | 337 | 18% |
Unknown | 411 | 22% |