Tan, X., Lyu, C., Umer, H.M. et al. (7 more authors) (2025) SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations). 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations), 29 Apr - 04 May 2025, New Mexico, USA. Association for Computational Linguistics ISBN 979-8-89176-191-9
Abstract
Detecting toxic language, including sexism, harassment, and abusive behaviour, remains a critical challenge, particularly in its subtle and context-dependent forms. Existing approaches largely focus on isolated message-level classification, overlooking toxicity that emerges across conversational contexts. To promote and enable future research in this direction, we introduce *SafeSpeech*, a comprehensive platform for toxic content detection and analysis that bridges message-level and conversation-level insights. The platform integrates fine-tuned classifiers and large language models (LLMs) to enable multi-granularity detection, toxic-aware conversation summarization, and persona profiling. *SafeSpeech* also incorporates explainability mechanisms, such as perplexity gain analysis, to highlight the linguistic elements driving predictions. Evaluations on benchmark datasets, including EDOS, OffensEval, and HatEval, demonstrate the reproduction of state-of-the-art performance across multiple tasks, including fine-grained sexism detection.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | ©2025 Association for Computational Linguistics. This is an open access article under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number Dorset Police *KRISTAL* 79666 |
Depositing User: | Symplectic Publications |
Date Deposited: | 21 May 2025 11:29 |
Last Modified: | 21 May 2025 11:29 |
Published Version: | https://aclanthology.org/2025.naacl-demo.31/ |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:226918 |