# Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics

arXiv: https://arxiv.org/abs/2206.03390 · HTML: https://mlsanity.com/paper/2206.03390/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 61 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection](https://mlsanity.com/paper/2007.11464/) (2020)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Evaluating the Underlying Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.08783/) (2019)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models](https://mlsanity.com/paper/2110.00672/) (2021)
- [The Grey Hoodie Project: Big Tobacco, Big Tech, and the threat on academic integrity](https://mlsanity.com/paper/2009.13676/) (2020)
- [Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation](https://mlsanity.com/paper/2005.00965/) (2020)
- [Factors Influencing the Surprising Instability of Word Embeddings](https://mlsanity.com/paper/1804.09692/) (2018)
- [Evidence for Hypodescent in Visual Semantic AI](https://mlsanity.com/paper/2205.10764/) (2022)
- [Markedness in Visual Semantic AI](https://mlsanity.com/paper/2205.11378/) (2022)
- [ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries](https://mlsanity.com/paper/2006.03950/) (2020)
- [VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models](https://mlsanity.com/paper/2203.07504/) (2022)

## Built on by (most cited first, 24 of 24)

- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [American == White in Multimodal Language-and-Image AI](https://mlsanity.com/paper/2207.00691/) (2022)
- [ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages](https://mlsanity.com/paper/2305.10510/) (2023)
- [On the Independence of Association Bias and Empirical Fairness in Language Models](https://mlsanity.com/paper/2304.10153/) (2023)
- [Unmasking Nationality Bias: A Study of Human Perception of Nationalities in AI-Generated Articles](https://mlsanity.com/paper/2308.04346/) (2023)
- [Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp](https://mlsanity.com/paper/2405.08209/) (2024)
- [TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning](https://mlsanity.com/paper/2404.19597/) (2024)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [Semantic and Expressive Variation in Image Captions Across Languages](https://mlsanity.com/paper/2310.14356/) (2023)
- [Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools](https://mlsanity.com/paper/2309.17337/) (2023)
- [Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships](https://mlsanity.com/paper/2407.12543/) (2024)
- [Conceptor-Aided Debiasing of Large Language Models](https://mlsanity.com/paper/2211.11087/) (2022)
- [Gender Bias in Machine Translation and The Era of Large Language Models](https://mlsanity.com/paper/2401.10016/) (2024)
- [Gender Bias in Transformer Models: A comprehensive survey](https://mlsanity.com/paper/2306.10530/) (2023)
- [A Taxonomy of Stereotype Content in Large Language Models](https://mlsanity.com/paper/2408.00162/) (2024)
- [GradBias: Unveiling Word Influence on Bias in Text-to-Image Generative Models](https://mlsanity.com/paper/2408.16700/) (2024)
- [Measuring Gender Bias in Job Title Matching for Grammatical Gender Languages](https://mlsanity.com/paper/2509.13803/) (2025)
- [ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning](https://mlsanity.com/paper/2401.16349/) (2024)
- [Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications](https://mlsanity.com/paper/2411.10544/) (2024)
- [Gender and Race Bias in Consumer Product Recommendations by Large Language Models](https://mlsanity.com/paper/2602.08124/) (2026)
- [Greater accessibility can amplify discrimination in generative AI](https://mlsanity.com/paper/2603.22260/) (2026)
- [Transparent Semantic Spaces: A Categorical Approach to Explainable Word Embeddings](https://mlsanity.com/paper/2508.20701/) (2025)
- [A Use-Case Specific Dataset for Measuring Dimensions of Responsible Performance in LLM-generated Text](https://mlsanity.com/paper/2510.20782/) (2025)
- [What Does Debiasing Really Remove? A Geometric Study of PCA-Based Gender Debiasing in Word Embeddings](https://mlsanity.com/paper/2606.07964/) (2026)

## Abstract (arXiv)

The statistical regularities in language corpora encode well-known social biases into word embeddings. Here, we focus on gender to provide a comprehensive analysis of group-based biases in widely-used static English word embeddings trained on internet corpora (GloVe 2014, fastText 2017). Using the Single-Category Word Embedding Association Test, we demonstrate the widespread prevalence of gender biases that also show differences in: (1) frequencies of words associated with men versus women; (b) part-of-speech tags in gender-associated words; (c) semantic categories in gender-associated words; and (d) valence, arousal, and dominance in gender-associated words. First, in terms of word frequency: we find that, of the 1,000 most frequent words in the vocabulary, 77% are more associated with men than women, providing direct evidence of a masculine default in the everyday language of the English-speaking world. Second, turning to parts-of-speech: the top male-associated words are typically verbs (e.g., fight, overpower) while the top female-associated words are typically adjectives and adverbs (e.g., giving, emotionally). Gender biases in embeddings also permeate parts-of-speech. Third, for semantic categories: bottom-up, cluster analyses of the top 1,000 words associated with each gender. The top male-associated concepts include roles and domains of big tech, engineering, religion, sports, and violence; in contrast, the top female-associated concepts are less focused on roles, including, instead, female-specific slurs and sexual content, as well as appearance and kitchen terms. Fourth, using human ratings of word valence, arousal, and dominance from a ~20,000 word lexicon, we find that male-associated words are higher on arousal and dominance, while female-associated words are higher on valence.