↓ Skip to main content

PNAS

Word embeddings quantify 100 years of gender and ethnic stereotypes

Overview of attention for article published in Proceedings of the National Academy of Sciences of the United States of America, April 2018
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • High Attention Score compared to outputs of the same age (99th percentile)
  • High Attention Score compared to outputs of the same age and source (95th percentile)

Mentioned by

news
16 news outlets
blogs
10 blogs
policy
3 policy sources
twitter
245 X users
facebook
1 Facebook page
googleplus
4 Google+ users

Citations

dimensions_citation
466 Dimensions

Readers on

mendeley
805 Mendeley
Title
Word embeddings quantify 100 years of gender and ethnic stereotypes
Published in
Proceedings of the National Academy of Sciences of the United States of America, April 2018
DOI 10.1073/pnas.1720347115
Pubmed ID
Authors

Nikhil Garg, Londa Schiebinger, Dan Jurafsky, James Zou

Abstract

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.

X Demographics

X Demographics

The data shown below were collected from the profiles of 245 X users who shared this research output. Click here to find out more about how the information was compiled.
Mendeley readers

Mendeley readers

The data shown below were compiled from readership statistics for 805 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
Unknown 805 100%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 170 21%
Student > Master 102 13%
Researcher 81 10%
Student > Bachelor 75 9%
Student > Doctoral Student 39 5%
Other 126 16%
Unknown 212 26%
Readers by discipline Count As %
Computer Science 171 21%
Social Sciences 127 16%
Psychology 60 7%
Business, Management and Accounting 37 5%
Linguistics 25 3%
Other 152 19%
Unknown 233 29%
Attention Score in Context

Attention Score in Context

This research output has an Altmetric Attention Score of 359. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 15 February 2024.
All research outputs
#89,092
of 25,392,582 outputs
Outputs from Proceedings of the National Academy of Sciences of the United States of America
#2,025
of 103,000 outputs
Outputs of similar age
#2,196
of 343,099 outputs
Outputs of similar age from Proceedings of the National Academy of Sciences of the United States of America
#49
of 1,017 outputs
Altmetric has tracked 25,392,582 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 99th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 103,000 research outputs from this source. They typically receive a lot more attention than average, with a mean Attention Score of 39.4. This one has done particularly well, scoring higher than 98% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 343,099 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 99% of its contemporaries.
We're also able to compare this research output to 1,017 others from the same source and published within six weeks on either side of this one. This one has done particularly well, scoring higher than 95% of its contemporaries.