Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes

2017/11/22 by Nikhil Garg, Londa Schiebinger, Dan Jurafsky +1 · 1 voice · 3 citations
Computer Science · Physics and Astronomy · Social Sciences · #Anthropology #Artificial intelligence #Cartography #Census #Computational and Text Analysis Methods #Computer science #Demography #Dynamics (music) #Embedding #Ethnic group #Geography #Immigration #Intersection (aeronautics) #Language and cultural evolution #Linguistics #Opinion Dynamics and Social Influence #Population #Sociology #Word (group theory) #Word embedding #cs.CL #cs.CY

paper · pdf · doi:10.1073/pnas.1720347115

arxiv created 2017/11/22 · arxiv published 2017/11/22 · openalex publication_date 2018/04/03 · arxiv updated 2018/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Word embeddings use vectors to represent words such that the geometry between vectors captures semantic relationship between the words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding can be leveraged to quantify changes in stereotypes and attitudes toward women and ethnic minorities in the 20th and 21st centuries in the United States. We integrate word embeddings trained on 100 years of text data with the U.S. Census to show that changes in the embedding track closely with demographic and occupation shifts over time. The embedding captures global social shifts -- e.g., the women's movement in the 1960s and Asian immigration into the U.S -- and also illuminates how specific adjectives and occupations became more closely associated with certain populations over time. Our framework for temporal analysis of word embedding opens up a powerful new intersection between machine learning and quantitative social science.

Citations

• Efficient Estimation of Word Representations in Vector Space
• A model of (often mixed) stereotype content: Competence and warmth respectively follow from perceived status and competition.
• Glove: Global Vectors for Word Representation
• Stereotyping and Bias in the Flickr30K Dataset
• Dynamic Bernoulli Embeddings for Language Evolution
• Semantics derived automatically from language corpora contain human-like biases

Cited by

• Semantic Structure of Feature Space in Large Language Models
• Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning
• A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle

Discussions

• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes From Nov 2017 arxiv.org/abs/1711.08412 [bsky, 1 points, 0 comments]

Related

• Quantifying and Reducing Stereotypes in Word Embeddings
• When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?
• Gendered Cultural Discourse in Japan across the Prewar-Postwar Transition: Evidence from Historical Word Embeddings
• Word Embeddings Track Social Group Changes Across 70 Years in China
• An Improved Historical Embedding without Alignment