The Risk of Racial Bias in Hate Speech Detection

Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. Smith


Abstract
We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface markers of African American English (AAE) and ratings of toxicity in several widely-used hate speech datasets. Then, we show that models trained on these corpora acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others. Finally, we propose *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.
Anthology ID:
P19-1163
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1668–1678
Language:
URL:
https://aclanthology.org/P19-1163
DOI:
10.18653/v1/P19-1163
Bibkey:
Cite (ACL):
Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, and Noah A. Smith. 2019. The Risk of Racial Bias in Hate Speech Detection. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1668–1678, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
The Risk of Racial Bias in Hate Speech Detection (Sap et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1163.pdf
Video:
 https://vimeo.com/384485590