Abstract
Hate speech detection is an actively growing field of research with a variety of recently proposed approaches that allowed to push the state-of-the-art results. One of the challenges of such automated approaches – namely recent deep learning models – is a risk of false positives (i.e., false accusations), which may lead to over-blocking or removal of harmless social media content in applications with little moderator intervention. We evaluate deep learning models both under in-domain and cross-domain hate speech detection conditions, and introduce an SVM approach that allows to significantly improve the state-of-the-art results when combined with the deep learning models through a simple majority-voting ensemble. The improvement is mainly due to a reduction of the false positive rate.- Anthology ID:
- 2021.nlp4if-1.3
- Volume:
- Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NLP4IF
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 17–22
- Language:
- URL:
- https://aclanthology.org/2021.nlp4if-1.3
- DOI:
- 10.18653/v1/2021.nlp4if-1.3
- Cite (ACL):
- Ilia Markov and Walter Daelemans. 2021. Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate. In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 17–22, Online. Association for Computational Linguistics.
- Cite (Informal):
- Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate (Markov & Daelemans, NLP4IF 2021)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.nlp4if-1.3.pdf
- Data
- Hate Speech, OLID