Predicting personality from patterns of behavior collected with smartphones
Abstract
Smartphones are sensor-rich computers that can easily be used to collect extensive records of behaviors, posing serious threats to individuals' privacy. This study examines the extent to which individuals' personality dimensions (assessed at broad domain and narrow facet levels) can be predicted from six classes of behavior: 1) communication and social behavior, 2) music consumption, 3) app usage, 4) mobility, 5) overall phone activity, and 6) day- and night-time activity, in a large sample. The cross-validated results show which Big Five personality dimensions are predictable and which specific patterns of behavior are indicative of which dimensions, revealing communication and social behavior as most predictive overall. Our results highlight the benefits and dangers posed by the widespread collection of smartphone data.
- Publication:
-
Proceedings of the National Academy of Science
- Pub Date:
- July 2020
- DOI:
- 10.1073/pnas.1920484117
- Bibcode:
- 2020PNAS..11717680S