Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes

TL;DR

This paper presents a framework that uses temporal word embeddings to quantify and analyze 100 years of social stereotypes and attitudes towards women and ethnic minorities in the U.S., revealing how language reflects societal changes.

Contribution

It introduces a novel method for analyzing the evolution of social stereotypes over time using word embeddings aligned with demographic data.

Findings

Embedding tracks demographic and occupational shifts over a century.

Captures social movements like the women's movement and Asian immigration.

Reveals changing associations of adjectives and occupations with groups.

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.