@inproceedings{tan-etal-2025-safespeech,
title = "{S}afe{S}peech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations",
author = "Tan, Xingwei and
Lyu, Chen and
Umer, Hafiz Muhammad and
Khan, Sahrish and
Parvatham, Mahathi and
Arthurs, Lois and
Cullen, Simon and
Wilson, Shelley and
Jhumka, Arshad and
Pergola, Gabriele",
editor = "Dziri, Nouha and
Ren, Sean (Xiang) and
Diao, Shizhe",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-demo.31/",
doi = "10.18653/v1/2025.naacl-demo.31",
pages = "361--382",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2025-safespeech">
<titleInfo>
<title>SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingwei</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hafiz</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Umer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahrish</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahathi</namePart>
<namePart type="family">Parvatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lois</namePart>
<namePart type="family">Arthurs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Cullen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shelley</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arshad</namePart>
<namePart type="family">Jhumka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Pergola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="given">(Xiang)</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhe</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-191-9</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">tan-etal-2025-safespeech</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-demo.31</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-demo.31/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>361</start>
<end>382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations
%A Tan, Xingwei
%A Lyu, Chen
%A Umer, Hafiz Muhammad
%A Khan, Sahrish
%A Parvatham, Mahathi
%A Arthurs, Lois
%A Cullen, Simon
%A Wilson, Shelley
%A Jhumka, Arshad
%A Pergola, Gabriele
%Y Dziri, Nouha
%Y Ren, Sean (Xiang)
%Y Diao, Shizhe
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-191-9
%F tan-etal-2025-safespeech
%X 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.
%R 10.18653/v1/2025.naacl-demo.31
%U https://aclanthology.org/2025.naacl-demo.31/
%U https://doi.org/10.18653/v1/2025.naacl-demo.31
%P 361-382
Markdown (Informal)
[SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations](https://aclanthology.org/2025.naacl-demo.31/) (Tan et al., NAACL 2025)
ACL
- Xingwei Tan, Chen Lyu, Hafiz Muhammad Umer, Sahrish Khan, Mahathi Parvatham, Lois Arthurs, Simon Cullen, Shelley Wilson, Arshad Jhumka, and Gabriele Pergola. 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), pages 361–382, Albuquerque, New Mexico. Association for Computational Linguistics.