@inproceedings{bensalem-etal-2023-offensive,
title = "Offensive Language Detection in {A}rabizi",
author = "Bensalem, Imene and
Mout, Meryem and
Rosso, Paolo",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.36",
doi = "10.18653/v1/2023.arabicnlp-1.36",
pages = "423--434",
abstract = "Detecting offensive language in under-resourced languages presents a significant real-world challenge for social media platforms. This paper is the first work focused on the issue of offensive language detection in Arabizi, an under-explored topic in an under-resourced form of Arabic. For the first time, a comprehensive and critical overview of the existing work on the topic is presented. In addition, we carry out experiments using different BERT-like models and show the feasibility of detecting offensive language in Arabizi with high accuracy. Throughout a thorough analysis of results, we emphasize the complexities introduced by dialect variations and out-of-domain generalization. We use in our experiments a dataset that we have constructed by leveraging existing, albeit limited, resources. To facilitate further research, we make this dataset publicly accessible to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bensalem-etal-2023-offensive">
<titleInfo>
<title>Offensive Language Detection in Arabizi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imene</namePart>
<namePart type="family">Bensalem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">Mout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Rosso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting offensive language in under-resourced languages presents a significant real-world challenge for social media platforms. This paper is the first work focused on the issue of offensive language detection in Arabizi, an under-explored topic in an under-resourced form of Arabic. For the first time, a comprehensive and critical overview of the existing work on the topic is presented. In addition, we carry out experiments using different BERT-like models and show the feasibility of detecting offensive language in Arabizi with high accuracy. Throughout a thorough analysis of results, we emphasize the complexities introduced by dialect variations and out-of-domain generalization. We use in our experiments a dataset that we have constructed by leveraging existing, albeit limited, resources. To facilitate further research, we make this dataset publicly accessible to the research community.</abstract>
<identifier type="citekey">bensalem-etal-2023-offensive</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.36</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.36</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>423</start>
<end>434</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Offensive Language Detection in Arabizi
%A Bensalem, Imene
%A Mout, Meryem
%A Rosso, Paolo
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F bensalem-etal-2023-offensive
%X Detecting offensive language in under-resourced languages presents a significant real-world challenge for social media platforms. This paper is the first work focused on the issue of offensive language detection in Arabizi, an under-explored topic in an under-resourced form of Arabic. For the first time, a comprehensive and critical overview of the existing work on the topic is presented. In addition, we carry out experiments using different BERT-like models and show the feasibility of detecting offensive language in Arabizi with high accuracy. Throughout a thorough analysis of results, we emphasize the complexities introduced by dialect variations and out-of-domain generalization. We use in our experiments a dataset that we have constructed by leveraging existing, albeit limited, resources. To facilitate further research, we make this dataset publicly accessible to the research community.
%R 10.18653/v1/2023.arabicnlp-1.36
%U https://aclanthology.org/2023.arabicnlp-1.36
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.36
%P 423-434
Markdown (Informal)
[Offensive Language Detection in Arabizi](https://aclanthology.org/2023.arabicnlp-1.36) (Bensalem et al., ArabicNLP-WS 2023)
ACL
- Imene Bensalem, Meryem Mout, and Paolo Rosso. 2023. Offensive Language Detection in Arabizi. In Proceedings of ArabicNLP 2023, pages 423–434, Singapore (Hybrid). Association for Computational Linguistics.