@inproceedings{botella-gil-etal-2025-balancing,
title = "Balancing the Scales: Addressing Gender Bias in Social Media Toxicity Detection",
author = "Botella-Gil, Beatriz and
Consuegra-Ayala, Juan Pablo and
Bonet-Jover, Alba and
Moreda-Pozo, Paloma",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.23/",
pages = "194--203",
abstract = "The detection of toxic content in social media has become a critical task in Natural Language Processing (NLP), particularly given its intersection with complex issues like subjectivity, implicit language, and cultural context. Among these challenges, bias in training data remains a central concern{---}especially as language models risk reproducing and amplifying societal inequalities. This paper investigates the interplay between toxicity and gender bias on Twitter/X by introducing a novel dataset of violent and non-violent tweets, annotated not only for violence but also for gender. We conduct an exploratory analysis of how biased data can distort toxicity classification and present algorithms to mitigate these effects through dataset balancing and debiasing. Our contributions include four new dataset splits{---}two balanced and two debiased{---}that aim to support the development of fairer and more inclusive NLP models. By foregrounding the importance of equity in data curation, this work lays the groundwork for more ethical approaches to automated violence detection and gender annotation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="botella-gil-etal-2025-balancing">
<titleInfo>
<title>Balancing the Scales: Addressing Gender Bias in Social Media Toxicity Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatriz</namePart>
<namePart type="family">Botella-Gil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Pablo</namePart>
<namePart type="family">Consuegra-Ayala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alba</namePart>
<namePart type="family">Bonet-Jover</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Moreda-Pozo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The detection of toxic content in social media has become a critical task in Natural Language Processing (NLP), particularly given its intersection with complex issues like subjectivity, implicit language, and cultural context. Among these challenges, bias in training data remains a central concern—especially as language models risk reproducing and amplifying societal inequalities. This paper investigates the interplay between toxicity and gender bias on Twitter/X by introducing a novel dataset of violent and non-violent tweets, annotated not only for violence but also for gender. We conduct an exploratory analysis of how biased data can distort toxicity classification and present algorithms to mitigate these effects through dataset balancing and debiasing. Our contributions include four new dataset splits—two balanced and two debiased—that aim to support the development of fairer and more inclusive NLP models. By foregrounding the importance of equity in data curation, this work lays the groundwork for more ethical approaches to automated violence detection and gender annotation.</abstract>
<identifier type="citekey">botella-gil-etal-2025-balancing</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.23/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>194</start>
<end>203</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Balancing the Scales: Addressing Gender Bias in Social Media Toxicity Detection
%A Botella-Gil, Beatriz
%A Consuegra-Ayala, Juan Pablo
%A Bonet-Jover, Alba
%A Moreda-Pozo, Paloma
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F botella-gil-etal-2025-balancing
%X The detection of toxic content in social media has become a critical task in Natural Language Processing (NLP), particularly given its intersection with complex issues like subjectivity, implicit language, and cultural context. Among these challenges, bias in training data remains a central concern—especially as language models risk reproducing and amplifying societal inequalities. This paper investigates the interplay between toxicity and gender bias on Twitter/X by introducing a novel dataset of violent and non-violent tweets, annotated not only for violence but also for gender. We conduct an exploratory analysis of how biased data can distort toxicity classification and present algorithms to mitigate these effects through dataset balancing and debiasing. Our contributions include four new dataset splits—two balanced and two debiased—that aim to support the development of fairer and more inclusive NLP models. By foregrounding the importance of equity in data curation, this work lays the groundwork for more ethical approaches to automated violence detection and gender annotation.
%U https://aclanthology.org/2025.ranlp-1.23/
%P 194-203
Markdown (Informal)
[Balancing the Scales: Addressing Gender Bias in Social Media Toxicity Detection](https://aclanthology.org/2025.ranlp-1.23/) (Botella-Gil et al., RANLP 2025)
ACL
- Beatriz Botella-Gil, Juan Pablo Consuegra-Ayala, Alba Bonet-Jover, and Paloma Moreda-Pozo. 2025. Balancing the Scales: Addressing Gender Bias in Social Media Toxicity Detection. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 194–203, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.