CoChat
Sign Up
Cited by 778Face Recognition and PerceptionFace recognition and analysisEvolutionary Psychology and Human Behavior

The DOI matches its Crossref record; 53 of the 66 references it cites were found in a registry or an index.

Deep neural networks are more accurate than humans at detecting sexual orientation from facial images.

Open access
Wang, Yilun, Kosinski, Michal·2018·Journal of Personality and Social Psychology
DOI 10.1037/pspa0000098

Published version of a preprint

Open this paper in CoChat — free account

Abstract

We show that faces contain much more information about sexual orientation than can be perceived or interpreted by the human brain. We used deep neural networks to extract features from 35,326 facial images. These features were entered into a logistic regression aimed at classifying sexual orientation. Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 71% of cases for women. Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person. Facial features employed by the classifier included both fixed (e.g., nose shape) and transient facial features (e.g., grooming style). Consistent with the prenatal hormone theory of sexual orientation, gay men and women tended to have gender-atypical facial morphology, expression, and grooming styles. Prediction models aimed at gender alone allowed for detecting gay males with 57% accuracy and gay females with 58% accuracy. Those findings advance our understanding of the origins of sexual orientation and the limits of human perception. Additionally, given that companies and governments are increasingly using computer vision algorithms to detect people's intimate traits, our findings expose a threat to the privacy and safety of gay men and women. (PsycINFO Database Record

Overview

Integrity signals

Registry

Crossref · 10.1037/pspa0000098

Cites

53 of 53 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 66 references

Cited by

Sorted by citations

Items 401–500 of 778

Related

See all

Metadata

Authors
Wang, Y., & Kosinski, M.
Affiliations
Stanford University (US)
ORCID
Kosinski, Michal
Venue
Journal of Personality and Social Psychology
Publisher
American Psychological Association (APA)
Published
2018-02
Volume
114
Issue
2
Pages
246-257
ISSN
  • 0022-3514 (ISSN-L)
  • 1939-1315
DOI
10.1037/pspa0000098
OpenAlex
W2781265533
Cited by
766
References
66
Citations by year
2026: 29 · 2025: 57 · 2024: 57 · 2023: 146 · 2022: 98 · 2021: 92 · 2020: 155 · 2019: 75 · 2018: 51
FWCI
55.54
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Personality and Social Psychology (publishedVersion)
  • PubMed (publishedVersion)
  • PsyArXiv (OSF Preprints) (submittedVersion)
  • OSF Preprints (OSF Preprints) (submittedVersion)
  • PsyArXiv (OSF Preprints) (submittedVersion, cc-by)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Evolutionary Psychology and Human Behavior
Keywords
face images, deep neural network, gay men, gay women, facial morphology, privacy, computer vision, logistic regression
MeSH terms
Facial Recognition, Deep Learning, Adult, Face, Female, Humans, Male, Social Perception, Sexuality

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review