Abstract
We present a dataset and classifier for detecting the language of white supremacist extremism, a growing issue in online hate speech. Our weakly supervised classifier is trained on large datasets of text from explicitly white supremacist domains paired with neutral and anti-racist data from similar domains. We demonstrate that this approach improves generalization performance to new domains. Incorporating anti-racist texts as counterexamples to white supremacist language mitigates bias.- Anthology ID:
- 2023.acl-short.17
- Original:
- 2023.acl-short.17v1
- Version 2:
- 2023.acl-short.17v2
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 172–185
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.17
- DOI:
- 10.18653/v1/2023.acl-short.17
- Cite (ACL):
- Michael Yoder, Ahmad Diab, David Brown, and Kathleen Carley. 2023. A Weakly Supervised Classifier and Dataset of White Supremacist Language. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 172–185, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- A Weakly Supervised Classifier and Dataset of White Supremacist Language (Yoder et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.17.pdf