@inproceedings{mubarak-etal-2021-arabic,
title = "{A}rabic Offensive Language on {T}witter: Analysis and Experiments",
author = "Mubarak, Hamdy and
Rashed, Ammar and
Darwish, Kareem and
Samih, Younes and
Abdelali, Ahmed",
editor = "Habash, Nizar and
Bouamor, Houda and
Hajj, Hazem and
Magdy, Walid and
Zaghouani, Wajdi and
Bougares, Fethi and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Touileb, Samia",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.13",
pages = "126--135",
abstract = "Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers useoffensive language. Lastly, we conduct many experiments to produce strong results (F1 =83.2) on the dataset using SOTA techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2021-arabic">
<titleInfo>
<title>Arabic Offensive Language on Twitter: Analysis and Experiments</title>
</titleInfo>
<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">Ammar</namePart>
<namePart type="family">Rashed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<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">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Hajj</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">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</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">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers useoffensive language. Lastly, we conduct many experiments to produce strong results (F1 =83.2) on the dataset using SOTA techniques.</abstract>
<identifier type="citekey">mubarak-etal-2021-arabic</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.13</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>126</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Offensive Language on Twitter: Analysis and Experiments
%A Mubarak, Hamdy
%A Rashed, Ammar
%A Darwish, Kareem
%A Samih, Younes
%A Abdelali, Ahmed
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Hajj, Hazem
%Y Magdy, Walid
%Y Zaghouani, Wajdi
%Y Bougares, Fethi
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F mubarak-etal-2021-arabic
%X Detecting offensive language on Twitter has many applications ranging from detecting/predicting bullying to measuring polarization. In this paper, we focus on building a large Arabic offensive tweet dataset. We introduce a method for building a dataset that is not biased by topic, dialect, or target. We produce the largest Arabic dataset to date with special tags for vulgarity and hate speech. We thoroughly analyze the dataset to determine which topics, dialects, and gender are most associated with offensive tweets and how Arabic speakers useoffensive language. Lastly, we conduct many experiments to produce strong results (F1 =83.2) on the dataset using SOTA techniques.
%U https://aclanthology.org/2021.wanlp-1.13
%P 126-135
Markdown (Informal)
[Arabic Offensive Language on Twitter: Analysis and Experiments](https://aclanthology.org/2021.wanlp-1.13) (Mubarak et al., WANLP 2021)
ACL