Private traits and attributes are predictable from digital records of human behavior
Bibliographic Data
| ID | 23369508 |
|---|---|
| Authors | Michal Kosinski (0000-0003-2936-4775, Free School Lane, The Psychometrics Centre, University of Cambridge, Cambridge CB2 3RQ United Kingdom; and), David Stillwell (0000-0003-0174-3212, Free School Lane, The Psychometrics Centre, University of Cambridge, Cambridge CB2 3RQ United Kingdom; and), Thore Graepel (0000-0003-3957-0310, Microsoft Research, Cambridge CB1 2FB, United Kingdom) |
| Year | 2013 |
| Volume | 110 |
| Issue | 15 |
| Pages | 5802-5805 |
| Publication date | 2013-04-09 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Proceedings of the National Academy of Sciences (JOURNAL) |
| Journal identifiers | ISSN: 0027-8424 • E-ISSN: 1091-6490 |
| Publisher | National Academy of Sciences (PUBLISHER • US) |
| DOI | 10.1073/pnas.1218772110 |
| PMID | 23479631 |
| PMCID | PMC3625324 |
| OpenAlex | W2153803020 |
| Language | EN |
| Citations received | 322 |
| References cited | 26 |
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.
Big Five personality traits · Logistic regression · Machine learning · Openness to experience · Personality · Sexual orientation · Test (biology) · Trait · Computer Science · Impact of Technology on Adolescents · LGBTQ Health, Identity, and Policy · Personality Traits and Psychology · Psychology · Social Psychology
Safety and Security
Smartphone Usage
Social Interaction and Interpersonal Relationships
Personality and Individual Differences
Toward an Interdisciplinary Model of Organized, Psychology-Based Persuasive Communication
Politik in der digitalen Gesellschaft
Smartphones within Psychological Science
Misperceptions of charismatic species' conservation status
Internet Privacy Rights
Una prima tassonomia delle sfide politiche poste dall’intelligenza artificiale
Acting on a hunch
Socjologia 2.0
Os Caminhos Da Avaliação Psicológica No Brasil E No Mundo
Should Artificial Intelligence Augment Medical Decision Making? The Case for an Autonomy Algorithm
Big Tech Dominance Despite Global Mistrust
Mercancía Audiencia en La Era De Las Plataformas
Da formação da indústria cultural brasileira à consolidação da indústria da publicidade
The Need to Connect, Predicting Personality, and the Brain’s Reward System
Psychopaths Online
When Politicians Talk
Digital Citizenship in the Russian Federation
Internet Discourse
In data we trust? The implications of datafication for social monitoring
The Banality of Cynicism
Biobancos genómicos nacionales
Artificial Intelligence and Human Rights
Classic banking
O Jornalismo na encruzilhada do ‘algorithmic turn’
PRIME biases of the digital age
(Not) hearing happiness
Economia psíquica dos algoritmos e laboratório de plataforma
The fall of a dry leaf is a warning to the green ones
Engineering the public
Posverdad y fake news en comunicación política
International law, surveillance and the protection of privacy
Encoding Equality
Fear of a Yellow Planet
The Caliphate Is Not a Tweet Away
Substance use and sentiment and topical tendencies
Internet profiling
Worrying Impact of Artificial Intelligence and Big Data Through the Prism of Recommender Systems
Diferencias De Opinión Sobre El Uso De Los Test
Comisión de Test
The data economy
Social creation networks for designing low income interfaces in programmable thermostats
Tratamiento de datos personales de las opiniones políticas en el marco electoral
El big data en los procesos políticos
Automatic personality assessment through social media language
Personal echo chambers
Facebook as a research tool for the social sciences
Profiles, Identities, Data
Limiting Access to Certain Anonymous Information
Discriminating Data
The Big Data Agenda
The Fifth Estate
Big Data und Governance im digitalen Zeitalter
Ambulatory Assessment
Personality, Gender, and Culture
Demokratische digitale Souveränität«
Optimising Emotions, Incubating Falsehoods
Inszenieren und Mobilisieren
Digital Platforms and Algorithmic Subjectivities
Thick Big Data
Data Subject Rights under the GDPR
The Right to Erasure in EU Data Protection Law
Was heißt digitale Souveränität?
Private Daten
The Psychology of Fake News
Privacy as Trust
Questionnaire Science
Frenemies
Computer-based personality judgments are more accurate than those made by humans
Predicting the Big 5 personality traits from digital footprints on social media
Choosing Prediction Over Explanation in Psychology
Siri, Siri, in my hand
“What do they snapchat about?” Patterns of use in time-limited instant messaging service
Taxonomy of Risks posed by Language Models
Understanding lurkers in online communities
Big Data's Disparate Impact
The Ethics of AI Ethics
Internet Research in Psychology
Facebook language predicts depression in medical records
Social Data
Psychological targeting as an effective approach to digital mass persuasion
Third wave positive psychology
The Emerging Neuroscience of Social Media
Personality Traits and Personal Values
Tweeting From Left to Right
Two social lives
Personality, Gender, and Age in the Language of Social Media
Smart advertising and online dictionary usefulness
One Size Fits All
Whose Lives Matter? Mass Shootings and Social Media Discourses of Sympathy and Policy, 2012–2014
Ciudadanía vigilada o monitorización ciudadana? Dos aproximaciones opuestas a la relación entre tecnología y democracia
The Human Connection Drug
Everybody Puts Their Whole Life on Facebook”
Use of Facebook by Hospitals in Taiwan
The Automation of Society is Next
Assessing Interests in the Twenty-First-Century Workforce
Adaptive Measurement and Assessment
The Raven's Progressive Matrices
Matrix Factorization Techniques for Recommender Systems
Computational Social Science
The Satisfaction With Life Scale
Life‐Satisfaction Is a Momentary Judgment and a Stable Personality Characteristic
Gaydar
The international personality item pool and the future of public-domain personality measures
Customary Killings in Turkey and Turkish Modernization
Personality in cyberspace
Introduction to the Special Section on Cognitive Abilities
Personality as manifest in word use
A room with a cue
The do re mi's of everyday life
Are both parents always better than one? Parental conflict and young adult well-being
| Unique citing works | 322 |
|---|---|
| Citations per year | 24,77 |
| Citation span | 2013 - 2026 (14) |
| Citation velocity | current |
| Highly cited | Yes |
| Citation types | Neutral: 272 |