Cargando…

Using word embeddings to investigate cultural biases

Word embeddings provide quantitative representations of word semantics and the associations between word meanings in text data, including in large repositories in media and social media archives. This article introduces social psychologists to word embedding research via a consideration of bias anal...

Descripción completa

Detalles Bibliográficos
Autores principales: Durrheim, Kevin, Schuld, Maria, Mafunda, Martin, Mazibuko, Sindisiwe
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10086990/
https://www.ncbi.nlm.nih.gov/pubmed/35871272
http://dx.doi.org/10.1111/bjso.12560
_version_ 1785022248628781056
author Durrheim, Kevin
Schuld, Maria
Mafunda, Martin
Mazibuko, Sindisiwe
author_facet Durrheim, Kevin
Schuld, Maria
Mafunda, Martin
Mazibuko, Sindisiwe
author_sort Durrheim, Kevin
collection PubMed
description Word embeddings provide quantitative representations of word semantics and the associations between word meanings in text data, including in large repositories in media and social media archives. This article introduces social psychologists to word embedding research via a consideration of bias analysis, a topic of central concern in the discipline. We explain how word embeddings are constructed and how they can be used to measure bias along bipolar dimensions that are comparable to semantic differential scales. We review recent studies that show how familiar social biases can be detected in embeddings and how these change over time and in conjunction with real‐world discriminatory practices. The evidence suggests that embeddings yield valid and reliable estimates of bias and that they can identify subtle biases that may not be communicated explicitly. We argue that word embedding research can extend scholarship on prejudice and stereotyping, providing measures of the bias environment of human thought and action.
format Online
Article
Text
id pubmed-10086990
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-100869902023-04-12 Using word embeddings to investigate cultural biases Durrheim, Kevin Schuld, Maria Mafunda, Martin Mazibuko, Sindisiwe Br J Soc Psychol Articles Word embeddings provide quantitative representations of word semantics and the associations between word meanings in text data, including in large repositories in media and social media archives. This article introduces social psychologists to word embedding research via a consideration of bias analysis, a topic of central concern in the discipline. We explain how word embeddings are constructed and how they can be used to measure bias along bipolar dimensions that are comparable to semantic differential scales. We review recent studies that show how familiar social biases can be detected in embeddings and how these change over time and in conjunction with real‐world discriminatory practices. The evidence suggests that embeddings yield valid and reliable estimates of bias and that they can identify subtle biases that may not be communicated explicitly. We argue that word embedding research can extend scholarship on prejudice and stereotyping, providing measures of the bias environment of human thought and action. John Wiley and Sons Inc. 2022-07-23 2023-01 /pmc/articles/PMC10086990/ /pubmed/35871272 http://dx.doi.org/10.1111/bjso.12560 Text en © 2022 The Authors. British Journal of Social Psychology published by John Wiley & Sons Ltd on behalf of British Psychological Society. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Articles
Durrheim, Kevin
Schuld, Maria
Mafunda, Martin
Mazibuko, Sindisiwe
Using word embeddings to investigate cultural biases
title Using word embeddings to investigate cultural biases
title_full Using word embeddings to investigate cultural biases
title_fullStr Using word embeddings to investigate cultural biases
title_full_unstemmed Using word embeddings to investigate cultural biases
title_short Using word embeddings to investigate cultural biases
title_sort using word embeddings to investigate cultural biases
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10086990/
https://www.ncbi.nlm.nih.gov/pubmed/35871272
http://dx.doi.org/10.1111/bjso.12560
work_keys_str_mv AT durrheimkevin usingwordembeddingstoinvestigateculturalbiases
AT schuldmaria usingwordembeddingstoinvestigateculturalbiases
AT mafundamartin usingwordembeddingstoinvestigateculturalbiases
AT mazibukosindisiwe usingwordembeddingstoinvestigateculturalbiases