Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media

Sayan Ghosh, Dylan Baker, David Jurgens, Vinodkumar Prabhakaran


Abstract
Online social media platforms increasingly rely on Natural Language Processing (NLP) techniques to detect abusive content at scale in order to mitigate the harms it causes to their users. However, these techniques suffer from various sampling and association biases present in training data, often resulting in sub-par performance on content relevant to marginalized groups, potentially furthering disproportionate harms towards them. Studies on such biases so far have focused on only a handful of axes of disparities and subgroups that have annotations/lexicons available. Consequently, biases concerning non-Western contexts are largely ignored in the literature. In this paper, we introduce a weakly supervised method to robustly detect lexical biases in broader geo-cultural contexts. Through a case study on a publicly available toxicity detection model, we demonstrate that our method identifies salient groups of cross-geographic errors, and, in a follow up, demonstrate that these groupings reflect human judgments of offensive and inoffensive language in those geographic contexts. We also conduct analysis of a model trained on a dataset with ground truth labels to better understand these biases, and present preliminary mitigation experiments.
Anthology ID:
2021.wnut-1.35
Volume:
Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
Month:
November
Year:
2021
Address:
Online
Editors:
Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
313–328
Language:
URL:
https://aclanthology.org/2021.wnut-1.35
DOI:
10.18653/v1/2021.wnut-1.35
Bibkey:
Cite (ACL):
Sayan Ghosh, Dylan Baker, David Jurgens, and Vinodkumar Prabhakaran. 2021. Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media. In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pages 313–328, Online. Association for Computational Linguistics.
Cite (Informal):
Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media (Ghosh et al., WNUT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wnut-1.35.pdf