Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words
Joan Serrà, Ilias Leontiadis, Dimitris Spathis, Gianluca Stringhini, Jeremy Blackburn, Athena Vakali
Abstract
Common approaches to text categorization essentially rely either on n-gram counts or on word embeddings. This presents important difficulties in highly dynamic or quickly-interacting environments, where the appearance of new words and/or varied misspellings is the norm. A paradigmatic example of this situation is abusive online behavior, with social networks and media platforms struggling to effectively combat uncommon or non-blacklisted hate words. To better deal with these issues in those fast-paced environments, we propose using the error signal of class-based language models as input to text classification algorithms. In particular, we train a next-character prediction model for any given class and then exploit the error of such class-based models to inform a neural network classifier. This way, we shift from the ‘ability to describe’ seen documents to the ‘ability to predict’ unseen content. Preliminary studies using out-of-vocabulary splits from abusive tweet data show promising results, outperforming competitive text categorization strategies by 4-11%.- Anthology ID:
- W17-3005
- Volume:
- Proceedings of the First Workshop on Abusive Language Online
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, BC, Canada
- Editors:
- Zeerak Waseem, Wendy Hui Kyong Chung, Dirk Hovy, Joel Tetreault
- Venue:
- ALW
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 36–40
- Language:
- URL:
- https://aclanthology.org/W17-3005
- DOI:
- 10.18653/v1/W17-3005
- Cite (ACL):
- Joan Serrà, Ilias Leontiadis, Dimitris Spathis, Gianluca Stringhini, Jeremy Blackburn, and Athena Vakali. 2017. Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words. In Proceedings of the First Workshop on Abusive Language Online, pages 36–40, Vancouver, BC, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words (Serrà et al., ALW 2017)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/W17-3005.pdf