@inproceedings{zaghouani-etal-2024-hateful,
title = "So Hateful! Building a Multi-Label Hate Speech Annotated {A}rabic Dataset",
author = "Zaghouani, Wajdi and
Mubarak, Hamdy and
Biswas, Md. Rafiul",
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.1308/",
pages = "15044--15055",
abstract = "Social media enables widespread propagation of hate speech targeting groups based on ethnicity, religion, or other characteristics. With manual content moderation being infeasible given the volume, automatic hate speech detection is essential. This paper analyzes 70,000 Arabic tweets, from which 15,965 tweets were selected and annotated, to identify hate speech patterns and train classification models. Annotators labeled the Arabic tweets for offensive content, hate speech, emotion intensity and type, effect on readers, humor, factuality, and spam. Key findings reveal 15{\%} of tweets contain offensive language while 6{\%} have hate speech, mostly targeted towards groups with common ideological or political affiliations. Annotations capture diverse emotions, and sarcasm is more prevalent than humor. Additionally, 10{\%} of tweets provide verifiable factual claims, and 7{\%} are deemed important. For hate speech detection, deep learning models like AraBERT outperform classical machine learning approaches. By providing insights into hate speech characteristics, this work enables improved content moderation and reduced exposure to online hate. The annotated dataset advances Arabic natural language processing research and resources."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-etal-2024-hateful">
<titleInfo>
<title>So Hateful! Building a Multi-Label Hate Speech Annotated Arabic Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Rafiul</namePart>
<namePart type="family">Biswas</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 media enables widespread propagation of hate speech targeting groups based on ethnicity, religion, or other characteristics. With manual content moderation being infeasible given the volume, automatic hate speech detection is essential. This paper analyzes 70,000 Arabic tweets, from which 15,965 tweets were selected and annotated, to identify hate speech patterns and train classification models. Annotators labeled the Arabic tweets for offensive content, hate speech, emotion intensity and type, effect on readers, humor, factuality, and spam. Key findings reveal 15% of tweets contain offensive language while 6% have hate speech, mostly targeted towards groups with common ideological or political affiliations. Annotations capture diverse emotions, and sarcasm is more prevalent than humor. Additionally, 10% of tweets provide verifiable factual claims, and 7% are deemed important. For hate speech detection, deep learning models like AraBERT outperform classical machine learning approaches. By providing insights into hate speech characteristics, this work enables improved content moderation and reduced exposure to online hate. The annotated dataset advances Arabic natural language processing research and resources.</abstract>
<identifier type="citekey">zaghouani-etal-2024-hateful</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1308/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15044</start>
<end>15055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T So Hateful! Building a Multi-Label Hate Speech Annotated Arabic Dataset
%A Zaghouani, Wajdi
%A Mubarak, Hamdy
%A Biswas, Md. Rafiul
%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 zaghouani-etal-2024-hateful
%X Social media enables widespread propagation of hate speech targeting groups based on ethnicity, religion, or other characteristics. With manual content moderation being infeasible given the volume, automatic hate speech detection is essential. This paper analyzes 70,000 Arabic tweets, from which 15,965 tweets were selected and annotated, to identify hate speech patterns and train classification models. Annotators labeled the Arabic tweets for offensive content, hate speech, emotion intensity and type, effect on readers, humor, factuality, and spam. Key findings reveal 15% of tweets contain offensive language while 6% have hate speech, mostly targeted towards groups with common ideological or political affiliations. Annotations capture diverse emotions, and sarcasm is more prevalent than humor. Additionally, 10% of tweets provide verifiable factual claims, and 7% are deemed important. For hate speech detection, deep learning models like AraBERT outperform classical machine learning approaches. By providing insights into hate speech characteristics, this work enables improved content moderation and reduced exposure to online hate. The annotated dataset advances Arabic natural language processing research and resources.
%U https://aclanthology.org/2024.lrec-main.1308/
%P 15044-15055
Markdown (Informal)
[So Hateful! Building a Multi-Label Hate Speech Annotated Arabic Dataset](https://aclanthology.org/2024.lrec-main.1308/) (Zaghouani et al., LREC-COLING 2024)
ACL