@inproceedings{dehghan-yanikoglu-2024-multi-domain,
title = "Multi-domain Hate Speech Detection Using Dual Contrastive Learning and Paralinguistic Features",
author = "Dehghan, Somaiyeh and
Yan{\i}ko{\u{g}}lu, Berrin",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1025",
pages = "11745--11755",
abstract = "Social networks have become venues where people can share and spread hate speech, especially when the platforms allow users to remain anonymous. Hate speech can have significant social and cultural effects, especially when it targets specific groups of people in terms of religion, race, ethnicity, culture or a specific social situation such as immigrants and refugees. In this study, we propose a hate speech detection model, BERTurk-DualCL, using a mixed objective with contrastive learning loss that is combined with the traditional cross-entropy loss used for classification. In addition, we study the effects of paralinguistic features, namely emojis and hashtags, on the performance of our model. We trained and evaluated our model on tweets in four different topics with heated discussions from two separate datasets, ranging from discussions about migrants to the Israel-Palestine conflict. Our multi-domain model outperforms comparable results in literature and the average results of four domain-specific models, achieving a macro-F1 score of 81.04{\%} and 58.89{\%} on two- and five-class tasks respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dehghan-yanikoglu-2024-multi-domain">
<titleInfo>
<title>Multi-domain Hate Speech Detection Using Dual Contrastive Learning and Paralinguistic Features</title>
</titleInfo>
<name type="personal">
<namePart type="given">Somaiyeh</namePart>
<namePart type="family">Dehghan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrin</namePart>
<namePart type="family">Yanıkoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social networks have become venues where people can share and spread hate speech, especially when the platforms allow users to remain anonymous. Hate speech can have significant social and cultural effects, especially when it targets specific groups of people in terms of religion, race, ethnicity, culture or a specific social situation such as immigrants and refugees. In this study, we propose a hate speech detection model, BERTurk-DualCL, using a mixed objective with contrastive learning loss that is combined with the traditional cross-entropy loss used for classification. In addition, we study the effects of paralinguistic features, namely emojis and hashtags, on the performance of our model. We trained and evaluated our model on tweets in four different topics with heated discussions from two separate datasets, ranging from discussions about migrants to the Israel-Palestine conflict. Our multi-domain model outperforms comparable results in literature and the average results of four domain-specific models, achieving a macro-F1 score of 81.04% and 58.89% on two- and five-class tasks respectively.</abstract>
<identifier type="citekey">dehghan-yanikoglu-2024-multi-domain</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1025</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11745</start>
<end>11755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-domain Hate Speech Detection Using Dual Contrastive Learning and Paralinguistic Features
%A Dehghan, Somaiyeh
%A Yanıkoğlu, Berrin
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dehghan-yanikoglu-2024-multi-domain
%X Social networks have become venues where people can share and spread hate speech, especially when the platforms allow users to remain anonymous. Hate speech can have significant social and cultural effects, especially when it targets specific groups of people in terms of religion, race, ethnicity, culture or a specific social situation such as immigrants and refugees. In this study, we propose a hate speech detection model, BERTurk-DualCL, using a mixed objective with contrastive learning loss that is combined with the traditional cross-entropy loss used for classification. In addition, we study the effects of paralinguistic features, namely emojis and hashtags, on the performance of our model. We trained and evaluated our model on tweets in four different topics with heated discussions from two separate datasets, ranging from discussions about migrants to the Israel-Palestine conflict. Our multi-domain model outperforms comparable results in literature and the average results of four domain-specific models, achieving a macro-F1 score of 81.04% and 58.89% on two- and five-class tasks respectively.
%U https://aclanthology.org/2024.lrec-main.1025
%P 11745-11755
Markdown (Informal)
[Multi-domain Hate Speech Detection Using Dual Contrastive Learning and Paralinguistic Features](https://aclanthology.org/2024.lrec-main.1025) (Dehghan & Yanıkoğlu, LREC-COLING 2024)
ACL