Word embeddings quantify 100 years of gender and ethnic stereotypes

Word embeddings are a powerful machine-learning framework that represents each English word by a vector. The geometric relationship between these vectors captures meaningful semantic relationships between the corresponding words. In this paper, we develop a framework to demonstrate how the temporal...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the National Academy of Sciences - PNAS 2018-04, Vol.115 (16), p.E3635-E3644
Main Authors: Garg, Nikhil, Schiebinger, Londa, Jurafsky, Dan, Zou, James
Format: Article
Language:English
Subjects:
Demographics
Embedded systems
Embedding
Ethnicity
Gender
Immigration
Learning algorithms
Machine learning
Minority & ethnic groups
Occupations
Physical Sciences
PNAS Plus
Social discrimination learning
Social Sciences
Stereotypes
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Word embeddings are a powerful machine-learning framework that represents each English word by a vector. The geometric relationship between these vectors captures meaningful semantic relationships between the corresponding words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding helps 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 y of text data with the US Census to show that changes in the embedding track closely with demographic and occupation shifts over time. The embedding captures societal shifts—e.g., the women’s movement in the 1960s and Asian immigration into the United States—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 fruitful intersection between machine learning and quantitative social science.
ISSN:0027-8424
1091-6490
DOI:10.1073/pnas.1720347115