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 accessPublished version of a preprint
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
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“For example, a recent paper used publicly available images of faces uploaded to a dating website as a way to train AI software to detect someone’s sexuality based on a small number of photos (Wang and Kosinski 2018). While the study received ethics committee approval, it raises further questions around consent, since it is implausible that the users of the dating website could or necessarily would”
From How to Design AI for Social Good: Seven Essential Factors (2020) · cites this paper as Wang and Kosinski 2018
In the citing paper
“For example, a study found that computer vision algorithms were used to ascertain sexual orientation of people by scrutinizing thousands of facial images taken from public profiles on a dating website (Wang and Kosinski, 2017).”
From SHIFTing artificial intelligence to be responsible in healthcare: a systematic review (2022) · cites this paper as Wang and Kosinski, 2017
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
Private traits and attributes are predictable from digital records of human behavior
Kosinski, M., Stillwell, D., & Graepel, T. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1218772110 · Cited by 2,829
Self-citationThe Evolutionary Psychology of Facial Beauty
Rhodes, G. (2005) · Annual Review of Psychology · doi:10.1146/annurev.psych.57.102904.190208 · Cited by 1,821
Inferences of competence from faces predict election outcomes
Todorov, A., Mandisodza, A. N., Goren, A., & Hall, C. C. (2005) · Science · doi:10.1126/science.1110589 · Cited by 1,508
Social Cognition: Thinking Categorically about Others
Macrae, C. N., & Bodenhausen, G. V. (2000) · Annual Review of Psychology · doi:10.1146/annurev.psych.51.1.93 · Cited by 1,432
The evolution of human skin coloration
Jablonski, N. G., & Chaplin, G. (2000) · Journal of Human Evolution · doi:10.1006/jhev.2000.0403 · Cited by 1,212
Kosiński, M., Matz, S., Gosling, S. D., Popov, V., & Stillwell, D. J. (2015) · American Psychologist · doi:10.1037/a0039210 · Cited by 1,031
Self-citation
Cited by
Sorted by citations
Items 501–600 of 778
Artificial Intelligence and Religious Freedom
Temperman, J. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0004 · Cited by 3
Artificial Intelligence and the Right to Liberty and Security
Golunova, V. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0003 · Cited by 1
Artificial Intelligence and Human Rights
Prifti, K., Quintavalla, A., & Temperman, J. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0029 · Cited by 1
Artificial Intelligence and Consumer Protection Rights
Li, S., Schütte, B., & Majewski, L. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0027 · Cited by 1
Smart Cities, Artificial Intelligence, and Public Law
Ranchordás, S. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0033 · Cited by 1
New Lines of Business Development: Artificial Intelligence in Business
Gandía, J. A. G., González‐Tejero, C. B., & Miguel, Á. J. Á. (2024) · Contributions to management science · doi:10.1007/978-3-031-58704-7_1 · Cited by 1
Polyak, M. D., & Senichenkova, Y. O. (2024) · doi:10.1109/neuront62606.2024.10585459 · Cited by 1
“Advanced neural network models can infer a person's sexual orientation [1] and political preferences [2] by analyzing facial images.”
BackgroundAı̈meur, E. (2025) · Human-computer interaction series · doi:10.1007/978-3-031-61375-3_9 · Cited by 2
Zheng, H., Li, H. F., Xiao, D., et al. (2024) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom63139.2024.00202 · Cited by 1
“However, deep learning [7, 8] has enabled the extraction of soft-biometric attributes [9, 10] from these images.”
The Evolution of Cyber Law: Protecting Privacy and Data in the Digital Age
Alifah, D. (2024) · LAWYER Jurnal Hukum · doi:10.58738/lawyer.v2i2.652 · Cited by 1
“For instance, questions arise about data ownership in AI-driven platforms or liability when autonomous systems malfunction (Wang & Kosinski, 2018).”
Trzewik, M., Navon, M., Moran, T., wardi, H., Langer, A., Hadad, B., Sofer, C., & Reggev, N. (2025) · Behavior Research Methods · doi:10.3758/s13428-025-02723-1 · Cited by 1
“Finally, researchers interested in generating a face dataset of specific underrepresented populations could collect multiple images of that population online through online browsers and social media (e.g., Bainbridge et al., 2013; Wang & Kosinski, 2018).”
A Portrait of the Computer as a Young Artist
Briel, H. (2018) · IAFOR Journal of Cultural Studies · doi:10.22492/ijcs.3.1.01 · Cited by 1
Social Media-Addiction: Personality traits and human biology in the Facebook-age
Kutschera, U. (2019) · Mental Health and Addiction Research · doi:10.15761/mhar.1000179 · Cited by 1
“This idea is hardly compatible with the empirical findings summarized above [6,7].”
BackgroundResultInfluentialDireitos Humanos, inteligência artificial e privacidade
Cassino, J. F., Avelino, R. D. S., & da Silveira, S. A. (2019) · Monções Revista de Relações Internacionais da UFGD · doi:10.30612/rmufgd.v8i15.11546 · Cited by 1
Application of recurrent and deep neural networks in classification tasks
de Campos, L. M. L., & Duarte, D. S. (2020) · Revista Gestão & Tecnologia · doi:10.20397/2177-6652/2020.v20i3.1709 · Cited by 1
The Right to Privacy as a Cornerstone of Human Individuality and Freedom?
Eaton, M. (2020) · Springer eBooks · doi:10.1007/978-3-030-55300-5_13 · Cited by 1
A Plea to Reflect on the Entanglements of Gendered Work Patterns and Digital Technologies
von Alemann, A., Gruhlich, J., Horwath, I., et al. (2021) · Gender and Research · doi:10.13060/gav.2020.009 · Cited by 1
“This is evident, for example, in the debates on the controversial ‘Gay Faces Study’, which examines the extent to which a person‘s sexual orientation can be determined solely from their face (see Wang, Kosinski 2017; Leuner 2018).”
BackgroundQueering Computing and Computing Education
Paré, D. (2021) · Libraries and Cultural Resources (University of Calgary) · doi:10.11575/prism/38685 · Cited by 1
Beispiele für problematische KI-Anwendungen
Bläsius, K. H. (2021) · Anwendungen und Konzepte der Wirtschaftsinformatik · doi:10.26034/lu.akwi.2021.3305 · Cited by 1
Digital Human in Cybersecurity Risk Assessment
Jurevičienė, A., Brilingaitė, A., & Bukauskas, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78114-9_29 · Cited by 1
What the Federal Government Owes Student Borrowers.
Combe, P. (2009) · The chronicle of higher education · Cited by 1
Leutner, F., Akhtar, R., & Chamorro‐Premuzic, T. (2022) · Emerald Group Publishing Limited eBooks · doi:10.1108/978-1-83867-559-220221004 · Cited by 1
Artivismo e a emergência de novas subjetividades políticas no pós-digital
Policarpo, C. (2022) · Pós-Limiar · doi:10.24220/2595-9557v5e2022a5635 · Cited by 1
Korngiebel, D. M., Solomonides, A. E., & Goodman, K. W. (2022) · Cognitive informatics in biomedicine and healthcare · doi:10.1007/978-3-031-09108-7_18 · Cited by 1
Artificial Intelligence and Gender-Based Discrimination
Lütz, F. (2023) · Oxford University Press eBooks · doi:10.1093/law/9780192882486.003.0014 · Cited by 1
Kosiński, M., & Behrend, T. S. (2018) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2017.12.006 · Cited by 1
Self-citationAutomatic Selection of MapReduce Machine Learning Algorithms: A Model Building Approach
Franklin, F. S. (2018) · Digital Commons - Michigan Tech (Michigan Technological University) · doi:10.37099/mtu.dc.etdr/604 · Cited by 1
Aichholzer, G., & Rose, G. (2019) · doi:10.1553/10.1007/978-3-030-27184-8 · Cited by 1
Latent Variable Machine Learning Algorithms: Applications in a Nuclear Physics Experiment
Solli, R. (2019) · NORA - Norwegian Open Research Archives · Cited by 1
Social Interaction and Interpersonal Relationships
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.005 · Cited by 1
Top-K Deep Video Analytics: A Probabilistic ApproachPreprint
Lai, Z., Han, C., Liu, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.00773 · Cited by 1
“Such developments have created great demands on practical analytics over video data [31, 25, 36, 5, 51].”
BackgroundExcavating “Excavating AI”: The Elephant in the GalleryPreprint
Lyons, M. J. (2021) · doi:10.31234/osf.io/8arv5 · Cited by 1
Das Privacy Paradox aus psychologischer PerspektivePreprint
Dienlin, T. (2021) · doi:10.31235/osf.io/vbsg3 · Cited by 1
Putative Ratios of Facial Attractiveness in a Deep Neural NetworkPreprint
Tong, S., Liang, X., Kumada, T., et al. (2020) · doi:10.31234/osf.io/jsqdg · Cited by 1
Posts on Facebook by Schools and Districts and the Potential Risks to Students’ PrivacyPreprint
Rosenberg, J. M., Burchfield, M. A., Borchers, C., et al. (2021) · doi:10.31219/osf.io/ujyg2 · Cited by 1
Supervised machine learning methods in psychology: A practical introduction with annotated R codePreprint
Rosenbusch, H., Soldner, F., Evans, A. M., et al. (2019) · doi:10.31234/osf.io/s72vu · Cited by 1
Interrogating AI Bias through Digital Art
Zinn, Z. (2022) · doi:10.35650/jt.3039.d.2022 · Cited by 1
Predictability Hypotheses: A Meta-Theoretical and Methodological IntroductionPreprint
van Loon, A. (2022) · doi:10.31235/osf.io/s7uer · Cited by 1
Visual Privacy: Current and Emerging Regulations Around Unconsented Video Analytics in RetailPreprint
Pletcher, S. N. (2022) · doi:10.31219/osf.io/tfw96 · Cited by 1
“…(p. 4) Some studies claim to be able to derive ones political orientation, sexual orientation, criminal inclination and genetic disorders from a person’s face using video analytics and machine learning techniques (Gurovich et al., 2019; Kosinski, 2021; Wang & Kosinski, 2018; Wu & Zhang, 2019).”
Gabrieli, G. (2021) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/163958 · Cited by 1
Will You Have Autonomy in the Metaverse?Preprint
Geddes, K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4524680 · Cited by 1
Floridi, L. (2023) · Oxford University Press eBooks · doi:10.1093/oso/9780198883098.002.0003 · Cited by 1
Dorobantu, M. (2020) · theses.fr (ABES) · doi:10.70675/29312bb2z62e4z4c9dza418z1499edfa0677 · Cited by 1
Regulating AI: Where U.S. State Policy and HCI (Mis)align
Migineishvili, N., Gao, A., Adjagbodjou, A. D., Thakur, D., Just, R., & Reinecke, K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791424
“Academics, industry professionals, and the public are therefore calling upon policymakers to define the role that AI will play in our emerging society given uncertainties around job displacement [15, 74], privacy threats, or algorithmic bias [10, 37, 73, 104, 107].”
Gay Genes? Genetics and Sexual Orientation
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.011
Frehse, G., & Althoff, M. (2017) · Institute of Science and Technology Austria
Modifiers of patients' Emergency Department care-seeking behavior
Nordberg, M. E. (2018) · Figshare
Chun, W., Hong, S., Huh, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.03444
“Thus, as presented in [4], if CNN is used to leak a very private matter of individuals, it is very hard to prevent CNN from exposing the privacy because we do not know what noise can hamper the recognition of a CNN.”
BackgroundMintz, A. G. (2018) · Texto Digital · doi:10.5007/1807-9288.2018v14n1p75
Privacy, Polarization, and Passage of Divisive Laws
Johnson, B., & Laskowski, P. (2018) · IEEE Symposium on Privacy-Aware Computing (PAC) · doi:10.1109/pac.2018.00007
“Machine learning algorithms have been shown to detect sexual orientation from facial images with more accuracy than humans [44].”
BackgroundIntimität und der Verlust der Informationskontrolle
Hagendorff, T. (2018) · Springer eBooks · doi:10.1007/978-3-658-24052-3_9
Ethics of Artificial Intelligence Demarcations
Hanssen, A. B., & Nichele, S. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-35664-4_13 · Cited by 1
Weizman, A. (2018) · eiuc.gc.repository · doi:10.25330/1826
Digital Normativity: A challenge for human subjectivization and free willPreprint
Fourneret, É., & Yvert, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.09735
“They have also shown greater efficacy than humans in inferring the sexual orientation of an individual based on only a few images [15].”
BackgroundPereira, K. J. (2019) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.47.2019.tde-10092019-152911
Performing algorithms: Automation and accident
Dockray, S. (2019) · Minerva Access (University of Melbourne)
Theory In, Theory Out: The uses of social theory in machine learning for social sciencePreprint
Radford, J. P., & Joseph, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.03203
“For example, following misguided intuitions about sexuality and its causes can lead to incorrect claims, made on top of poor research design decisions, about the biological nature of sexuality (Wang and Kosinski, 2018).”
BackgroundMethods of Researching Online Communities
Jemielniak, D. (2020) · Oxford University Press eBooks · doi:10.1093/oso/9780198839705.003.0003
Ausloos, J. (2020) · doi:10.1093/oso/9780198847977.003.0005
Conditions of the Right to Erasure
Ausloos, J. (2020) · doi:10.1093/oso/9780198847977.003.0004
Open Questions on Balancing in the GDPR
Ausloos, J. (2020) · doi:10.1093/oso/9780198847977.003.0007
The Right to Erasure in Practice
Ausloos, J. (2020) · doi:10.1093/oso/9780198847977.003.0008
Ausloos, J. (2020) · doi:10.1093/oso/9780198847977.003.0003
Gender Classification and Bias Mitigation in Facial ImagesPreprint
Wu, W., Protopapas, P., Yang, Z., & Michalatos, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06141
“…[16], who used deep neural networks to detect white males’ sexuality. controversial research implied that facial images of the LGBTQ population have distinct characteristics from the heterosexual population – LGBTQ population tends to have atypical gender expression and grooming styles [16].”
BackgroundQUEER DE/STABILIZATIONS IN AND OF DIGITAL CULTURAL RESEARCH
Dobson, A. S., Race, K., & O’Riordan, K. (2019) · AoIR Selected Papers of Internet Research · doi:10.5210/spir.v2019i0.10971
Purely Bayesian counterfactuals versus Newcomb's paradoxPreprint
Hoang, L. N. (2020) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2008.04256
Die Moral der Maschinen – Können neuronale Netze ethische Grundsätze erlernen?
Davin, J. (2020) · Springer eBooks · doi:10.1007/978-3-658-30525-3_12
Inference of a universal social scale and segregation measures using social connectivity kernelsPreprint
Hoffmann, T., & Jones, N. S. (2020) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/5ecgp
FusiformNet: Extracting Discriminative Facial Features on Different LevelsPreprint
Takano, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.00577
“One potential example is psychological analyses of associations between certain personal attributes and facial features [23, 24, 25].”
BackgroundExplaining Explanation Methods.
Guidotti, R. (2020) · CINECA IRIS Institutial research information system (University of Pisa)
Bećirović, N., Bejtović, I., & Kevrić, J. (2021) · Journal of Natural Sciences and Engineering · doi:10.14706/jonsae2021315
Ustin, P. N., Popov, L. M., Khakimzyanov, R. N., & Vakhitov, G. (2021) · Autumn Conferences of Sports Science · doi:10.14198/jhse.2021.16.proc2.22
“The work of M. Kosinski (2017) about predicting possible behavioural reactions of a person through the coefficients of the ratio of the parameters of his face: width to height and the work about predicting sexual orientations of a person through its photo images (Wang & Kosinski, 2018).”
Definitions of Technical Terms
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.015
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.005
Genetic Information and How It Flows
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.003 · Cited by 1
Genes and Environments in Human Development
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.004
Genes, Personality and Personality Disorders
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.008
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.006
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.013
Statistical Significance Revisited
Tormählen, M., Klinkova, G., & Grabinski, M. (2021) · Mathematics · doi:10.3390/math9090958
Multi-concept adversarial attacksPreprint
Belavadi, V., Zhou, Y., Kantarcıoğlu, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.10287
“For example, an ML model may be trained to predict privacy-sensitive information such as sexual orientation and/or political affiliation using social network profiles [11, 21, 27].”
MethodComputational Social Science: A Thematic Review
Meckin, R., & Elliot, M. J. (2021) · NCRM EPrints Repository (National Centre for Research Methods)
Unny, B., & Bhatt, N. (2021) · International Journal of Information Security and Privacy · doi:10.4018/ijisp.285580
Hoofnagle, C. J., & Garfinkel, S. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108883719.019
Konstytucyjne wartości u progu ery sztucznej inteligencji
Pszczyński, M. (2021) · Przegląd Prawa Konstytucyjnego · doi:10.15804/ppk.2021.05.40
Hoofnagle, C. J., & Garfinkel, S. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108883719.016
Genes, Religiosity and Political Commitment
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.010
Genes, Education and Intelligence
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.007
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.008
Schmitt, É. (2020) · Big Data · doi:10.1002/9781119777014.refs
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.012
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.001
Genes, Food, Exercise and Weight
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.009
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.004
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.002
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.009
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.002
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.016
Alexander, D. R. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108566520.001
Ellis, D. A. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108671408.007
Metadata
- Authors
- Wang, Y., & Kosinski, M.
- Affiliations
- Stanford University (US)
- ORCID
- Kosinski, Michal
- Venue
- Journal of Personality and Social Psychology
- Published
- 2018-02
- Volume
- 114
- Issue
- 2
- Pages
- 246-257
- ISSN
- 0022-3514 (ISSN-L)
- 1939-1315
- 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
- green
- doi.org
- 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
