Gender Stereotypes in Natural Language: Word Embeddings Show Robust Consistency Across Child and Adult Language Corpora of More Than 65 Million Words
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Stereotypes are associations between social groups and semantic attributes that are widely shared within societies. The spoken and written language of a society affords a unique way to measure the magnitude and prevalence of these widely shared collective representations. Here, we used word embeddings to systematically quantify gender stereotypes in language corpora that are unprecedented in size (65+ million words) and scope (child and adult conversations, books, movies, TV). Across corpora, gender stereotypes emerged consistently and robustly for both theoretically selected stereotypes (e.g., work–home) and comprehensive lists of more than 600 personality traits and more than 300 occupations. Despite underlying differences across language corpora (e.g., time periods, formats, age groups), results revealed the pervasiveness of gender stereotypes in every corpus. Using gender stereotypes as the focal issue, we unite 19th-century theories of collective representations and 21st-century evidence on implicit social cognition to understand the subtle yet persistent presence of collective representations in language.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Fiske, S. T., Cuddy, A. J. C., Glick, P., & Xu, J. (2002) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.82.6.878 · Cited by 7,364 · cited 2×
“In Study 2, we focused on traits because they are a fundamental input to person perception (Fiske, Cuddy, Glick, & Xu, 2002) and are even made spontaneously without instruction.”
Semantics derived automatically from language corpora contain human-like biases
Caliskan, A., Bryson, J. J., & Narayanan, A. (2017) · Science · doi:10.1126/science.aal4230 · Cited by 2,887
Notes towards a description of social representations.
Moscovici, S. (1988) · European Journal of Social Psychology · doi:10.1002/ejsp.2420180303 · Cited by 2,003
Eagly, A. H., & Wood, W. (2012) · Handbook of Theories of Social Psychology · doi:10.4135/9781446249222.n49 · Cited by 1,853 · cited 6×
“Indeed, the strength of gender– occupation stereotypes was significantly correlated with real-world gender distribution of occupations, suggesting a coupling between language and direct experience of the real world (Eagly & Wood, 2012).”
InfluentialEagly, A. H., Nater, C., Miller, D. I., Kaufmann, M., & Sczesny, S. (2020) · American Psychologist · doi:10.1037/amp0000494 · Cited by 1,136 · cited 3×
“…psychological measures (e.g., on male–science/female–arts associations; Charlesworth & Banaji, 2019; Miller et al., 2018) but stand in contrast to trends of increasing (or stable) ste-reotypes for other domains (e.g., female–communion associations have increased over time; Eagly et al., 2020).”
Word embeddings quantify 100 years of gender and ethnic stereotypes
Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1720347115 · Cited by 1,065 · cited 4×
“…embed-dings have begun to be implemented more widely in psychology and adjacent fields and have been shown to be valid and reliable methods for capturing psychological and social phenomena (Caliskan et al., 2017; DeFranza et al., 2020; Garg et al., 2018; Kurdi et al., 2019; Lewis & Lupyan, 2020).”
InfluentialPatterns of gender development
Martin, C. L., & Ruble, D. N. (2010) · Annual Review of Psychology · doi:10.1146/annurev.psych.093008.100511 · Cited by 600 · cited 4×
“Despite previous work suggesting variation across children and adults in their magnitude of gender stereotypes and attitudes (Dunham et al., 2016; Martin & Ruble, 2010; Miller et al., 2018), the meta-regression suggests that, at least for these four well-studied domains, the language produced by…”
Influential
Cited by
Guo, W., & Caliskan, A. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462536 · Cited by 180
“Recent work has shown that human-like biases are embedded in the statistical regularities of language that are learned by word representations, namely word embeddings [4, 11, 13].”
BackgroundSchaerer, M., du Plessis, C., Nguyen, M. H. B., van Aert, R. C. M., Tiokhin, L., Lakens, D., Giulia Clemente, E., Pfeiffer, T., Dreber, A., Johannesson, M., et al. (2023) · Organizational Behavior and Human Decision Processes · doi:10.1016/j.obhdp.2023.104280 · Cited by 87
“More generally, empirical investigations suggest interrelationships and spillovers between only indirectly related dimensions of cultural change (Charlesworth & Banaji, 2022; Charlesworth, Yang, Mann, Kurdi, & Banaji, 2021; Norris & Inglehart, 2004; Varnum & Grossmann, 2016, 2017).”
Lehr, S. A., Caliskan, A., Liyanage, S., & Banaji, M. R. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2404328121 · Cited by 66
“More detailed statistical reporting may be found in SI Appendix , section S4 .”
InfluentialSelf-citationMoral stereotyping in large language models
Zewail, A., Figueroa, A., Graham, J., & Atari, M. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2519941123 · Cited by 29
Evidence for Hypodescent in Visual Semantic AI
Wolfe, R., Banaji, M. R., & Caliskan, A. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533185 · Cited by 19
Self-citation
Metadata
- Authors
- Charlesworth, T. E. S., Yang, V., Mann, T. C., Kurdi, B., & Banaji, M. R.
- Venue
- Psychological Science
- Publisher
- SAGE Publications
- Published
- 2021-01-05
- Volume
- 32
- Issue
- 2
- Pages
- 218-240
- ISSN
- 0956-7976 (ISSN-L)
- 1467-9280
- OpenAlex
- W3045825772
- Cited by
- 161
- References
- 7
- FWCI
- 39.38
- Type
- journal article
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.