Unsupervised Discovery of Implicit Gender Bias

Anjalie Field, Yulia Tsvetkov


Abstract
Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias against women at a comment level and present a model that can surface text likely to contain bias. Our main challenge is forcing the model to focus on signs of implicit bias, rather than other artifacts in the data. Thus, our methodology involves reducing the influence of confounds through propensity matching and adversarial learning. Our analysis shows how biased comments directed towards female politicians contain mixed criticisms, while comments directed towards other female public figures focus on appearance and sexualization. Ultimately, our work offers a way to capture subtle biases in various domains without relying on subjective human judgements.
Anthology ID:
2020.emnlp-main.44
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
596–608
Language:
URL:
https://aclanthology.org/2020.emnlp-main.44
DOI:
10.18653/v1/2020.emnlp-main.44
Bibkey:
Cite (ACL):
Anjalie Field and Yulia Tsvetkov. 2020. Unsupervised Discovery of Implicit Gender Bias. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 596–608, Online. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Discovery of Implicit Gender Bias (Field & Tsvetkov, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.44.pdf
Video:
 https://slideslive.com/38938782
Code
 anjalief/unsupervised_gender_bias