Gender Stereotypes in Natural Language: Word Embeddings Show Robust Consistency Across Child and Adult Language Corpora of More Than 65 Million Words

By Tessa E. S. Charlesworth, Victor Yang, Thomas C. Mann, Benedek Kurdi, Mahzarin R. Banaji. 2021

155 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Gender Studies, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Aylin Caliskan
2. Wei Guo
3. Sunipa Dev
4. Adina Williams
5. Percy Liang
6. Yulia Tsvetkov
7. Ruslan Salakhutdinov

In Gender Studies

1. Aylin Caliskan
2. Mahzarin R. Banaji
3. Wei Guo
4. Tessa E. S. Charlesworth
5. John T. Jost

In Sociology and Political Science

1. Aylin Caliskan
2. Wei Guo
3. Tessa E. S. Charlesworth
4. Mahzarin R. Banaji
5. Brian A. Nosek
6. A. Greenwald
7. Bertram Gawronski
8. Efrén O. Pérez

Citations in the corpus

• Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases (2020, background): “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].”
• Patterns of Implicit and Explicit Stereotypes III: Long-Term Change in Gender Stereotypes (2021, background): “For instance, the pervasive communication of gender stereotypes in language (e.g., Bolukbasi et al., 2016; Charlesworth et al., 2021) creates the perception that stereotypes are collective representations consensually held by everyone in society (Durkheim, 1924; Moscovici, 2000).”