Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces

Vanessa Hahn, Dana Ruiter, Thomas Kleinbauer, Dietrich Klakow


Abstract
Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.
Anthology ID:
2021.woah-1.2
Volume:
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
Month:
August
Year:
2021
Address:
Online
Venue:
WOAH
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6–16
Language:
URL:
https://aclanthology.org/2021.woah-1.2
DOI:
10.18653/v1/2021.woah-1.2
Bibkey:
Cite (ACL):
Vanessa Hahn, Dana Ruiter, Thomas Kleinbauer, and Dietrich Klakow. 2021. Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces. In Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pages 6–16, Online. Association for Computational Linguistics.
Cite (Informal):
Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces (Hahn et al., WOAH 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.woah-1.2.pdf
Video:
 https://aclanthology.org/2021.woah-1.2.mp4
Code
 uds-lsv/profane_subspaces