Doctoral School Seminar
24.06.2021 — Michał Kosiński (Stanford University): Predicting psychological traits from digital footprints
A growing proportion of human activities―such as social interactions, entertainment, shopping, and gathering information―are now mediated by digital devices and services. Such digitally mediated activities can be easily recorded, offering an unprecedented opportunity to study and assess psychological traits using actual (rather than self-reported) behavior. Our research shows that digital records of behavior―such as facial images, samples of text, Tweets, Facebook Likes, or web-browsing logs―can be used to accurately measure a wide range of psychological traits. Such predictions do not require participants' active involvement; can be easily and inexpensively applied to large populations; and are relatively immune to misrepresentation. Consequently, the predictability of psychological traits offers a promise to improve research and practice in fields ranging from psychology, sociology, and education to management and marketing. However, if applied unethically, the same models pose unprecedented risks to the privacy and well-being of entire societies.