Private traits and attributes are predictable from digital records of human behavior

We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into logistic/linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases. For the personality trait “Openness,” prediction accuracy is close to the test–retest accuracy of a standard personality test. We give examples of associations between attributes and Likes and discuss implications for online personalization and privacy.

Data and Resources
To access the resources you must log in
  • BibTeX filebibtex

    BibTex File

    The resource: 'BibTeX file' is not accessible as guest user. You must login to access it!
  • Conference PaperPDF

    The resource: 'Conference Paper' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Creator Kosinski, Michail
Creator Stillwell, David
Creator Graepel, Thore
DOI 10.1073/pnas.1218772110
Group Social Impact of AI and explainable ML
Publisher PNAS
Source Proceedings of the National Academy of Sciences of the United States of America
Thematic Cluster Privacy Enhancing Technology [PET]
system:type ConferencePaper
Management Info
Field Value
Version 1
Last Updated 8 September 2023, 17:01 (CEST)
Created 6 April 2021, 12:58 (CEST)