@inproceedings{vargas-etal-2023-socially,
title = "Socially Responsible Hate Speech Detection: Can Classifiers Reflect Social Stereotypes?",
author = {Vargas, Francielle and
Carvalho, Isabelle and
H{\"u}rriyeto{\u{g}}lu, Ali and
Pardo, Thiago and
Benevenuto, Fabr{\'\i}cio},
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.126",
pages = "1187--1196",
abstract = "Recent studies have shown that hate speech technologies may propagate social stereotypes against marginalized groups. Nevertheless, there has been a lack of realistic approaches to assess and mitigate biased technologies. In this paper, we introduce a new approach to analyze the potential of hate-speech classifiers to reflect social stereotypes through the investigation of stereotypical beliefs by contrasting them with counter-stereotypes. We empirically measure the distribution of stereotypical beliefs by analyzing the distinctive classification of tuples containing stereotypes versus counter-stereotypes in machine learning models and datasets. Experiment results show that hate speech classifiers attribute unreal or negligent offensiveness to social identity groups by reflecting and reinforcing stereotypical beliefs regarding minorities. Furthermore, we also found that models that embed expert and context information from offensiveness markers present promising results to mitigate social stereotype bias towards socially responsible hate speech detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vargas-etal-2023-socially">
<titleInfo>
<title>Socially Responsible Hate Speech Detection: Can Classifiers Reflect Social Stereotypes?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francielle</namePart>
<namePart type="family">Vargas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Pardo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabrício</namePart>
<namePart type="family">Benevenuto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</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>Recent studies have shown that hate speech technologies may propagate social stereotypes against marginalized groups. Nevertheless, there has been a lack of realistic approaches to assess and mitigate biased technologies. In this paper, we introduce a new approach to analyze the potential of hate-speech classifiers to reflect social stereotypes through the investigation of stereotypical beliefs by contrasting them with counter-stereotypes. We empirically measure the distribution of stereotypical beliefs by analyzing the distinctive classification of tuples containing stereotypes versus counter-stereotypes in machine learning models and datasets. Experiment results show that hate speech classifiers attribute unreal or negligent offensiveness to social identity groups by reflecting and reinforcing stereotypical beliefs regarding minorities. Furthermore, we also found that models that embed expert and context information from offensiveness markers present promising results to mitigate social stereotype bias towards socially responsible hate speech detection.</abstract>
<identifier type="citekey">vargas-etal-2023-socially</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.126</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>1187</start>
<end>1196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Socially Responsible Hate Speech Detection: Can Classifiers Reflect Social Stereotypes?
%A Vargas, Francielle
%A Carvalho, Isabelle
%A Hürriyetoğlu, Ali
%A Pardo, Thiago
%A Benevenuto, Fabrício
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F vargas-etal-2023-socially
%X Recent studies have shown that hate speech technologies may propagate social stereotypes against marginalized groups. Nevertheless, there has been a lack of realistic approaches to assess and mitigate biased technologies. In this paper, we introduce a new approach to analyze the potential of hate-speech classifiers to reflect social stereotypes through the investigation of stereotypical beliefs by contrasting them with counter-stereotypes. We empirically measure the distribution of stereotypical beliefs by analyzing the distinctive classification of tuples containing stereotypes versus counter-stereotypes in machine learning models and datasets. Experiment results show that hate speech classifiers attribute unreal or negligent offensiveness to social identity groups by reflecting and reinforcing stereotypical beliefs regarding minorities. Furthermore, we also found that models that embed expert and context information from offensiveness markers present promising results to mitigate social stereotype bias towards socially responsible hate speech detection.
%U https://aclanthology.org/2023.ranlp-1.126
%P 1187-1196
Markdown (Informal)
[Socially Responsible Hate Speech Detection: Can Classifiers Reflect Social Stereotypes?](https://aclanthology.org/2023.ranlp-1.126) (Vargas et al., RANLP 2023)
ACL