@inproceedings{bourgeade-etal-2023-learn,
title = "What Did You Learn To Hate? A Topic-Oriented Analysis of Generalization in Hate Speech Detection",
author = "Bourgeade, Tom and
Chiril, Patricia and
Benamara, Farah and
Moriceau, V{\'e}ronique",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.254",
doi = "10.18653/v1/2023.eacl-main.254",
pages = "3495--3508",
abstract = "Hate speech has unfortunately become a significant phenomenon on social media platforms, and it can cover various topics (misogyny, sexism, racism, xenophobia, etc.) and targets (e.g., black people, women). Various hate speech detection datasets have been proposed, some annotated for specific topics, and others for hateful speech in general. In either case, they often employ different annotation guidelines, which can lead to inconsistencies, even in datasets focusing on the same topics. This can cause issues in models trying to generalize across more data and more topics in order to improve detection accuracy. In this paper, we propose, for the first time, a topic-oriented approach to study generalization across popular hate speech datasets. We first perform a comparative analysis of the performances of Transformer-based models in capturing topic-generic and topic-specific knowledge when trained on different datasets. We then propose a novel, simple yet effective approach to study more precisely which topics are best captured in implicit manifestations of hate, showing that selecting combinations of datasets with better out-of-domain topical coverage improves the reliability of automatic hate speech detection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bourgeade-etal-2023-learn">
<titleInfo>
<title>What Did You Learn To Hate? A Topic-Oriented Analysis of Generalization in Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Bourgeade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patricia</namePart>
<namePart type="family">Chiril</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farah</namePart>
<namePart type="family">Benamara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Véronique</namePart>
<namePart type="family">Moriceau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hate speech has unfortunately become a significant phenomenon on social media platforms, and it can cover various topics (misogyny, sexism, racism, xenophobia, etc.) and targets (e.g., black people, women). Various hate speech detection datasets have been proposed, some annotated for specific topics, and others for hateful speech in general. In either case, they often employ different annotation guidelines, which can lead to inconsistencies, even in datasets focusing on the same topics. This can cause issues in models trying to generalize across more data and more topics in order to improve detection accuracy. In this paper, we propose, for the first time, a topic-oriented approach to study generalization across popular hate speech datasets. We first perform a comparative analysis of the performances of Transformer-based models in capturing topic-generic and topic-specific knowledge when trained on different datasets. We then propose a novel, simple yet effective approach to study more precisely which topics are best captured in implicit manifestations of hate, showing that selecting combinations of datasets with better out-of-domain topical coverage improves the reliability of automatic hate speech detection.</abstract>
<identifier type="citekey">bourgeade-etal-2023-learn</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.254</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.254</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>3495</start>
<end>3508</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Did You Learn To Hate? A Topic-Oriented Analysis of Generalization in Hate Speech Detection
%A Bourgeade, Tom
%A Chiril, Patricia
%A Benamara, Farah
%A Moriceau, Véronique
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F bourgeade-etal-2023-learn
%X Hate speech has unfortunately become a significant phenomenon on social media platforms, and it can cover various topics (misogyny, sexism, racism, xenophobia, etc.) and targets (e.g., black people, women). Various hate speech detection datasets have been proposed, some annotated for specific topics, and others for hateful speech in general. In either case, they often employ different annotation guidelines, which can lead to inconsistencies, even in datasets focusing on the same topics. This can cause issues in models trying to generalize across more data and more topics in order to improve detection accuracy. In this paper, we propose, for the first time, a topic-oriented approach to study generalization across popular hate speech datasets. We first perform a comparative analysis of the performances of Transformer-based models in capturing topic-generic and topic-specific knowledge when trained on different datasets. We then propose a novel, simple yet effective approach to study more precisely which topics are best captured in implicit manifestations of hate, showing that selecting combinations of datasets with better out-of-domain topical coverage improves the reliability of automatic hate speech detection.
%R 10.18653/v1/2023.eacl-main.254
%U https://aclanthology.org/2023.eacl-main.254
%U https://doi.org/10.18653/v1/2023.eacl-main.254
%P 3495-3508
Markdown (Informal)
[What Did You Learn To Hate? A Topic-Oriented Analysis of Generalization in Hate Speech Detection](https://aclanthology.org/2023.eacl-main.254) (Bourgeade et al., EACL 2023)
ACL