@inproceedings{abuzayed-elsayed-2020-quick,
title = "Quick and Simple Approach for Detecting Hate Speech in {A}rabic Tweets",
author = "Abuzayed, Abeer and
Elsayed, Tamer",
editor = "Al-Khalifa, Hend and
Magdy, Walid and
Darwish, Kareem and
Elsayed, Tamer and
Mubarak, Hamdy",
booktitle = "Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resource Association",
url = "https://aclanthology.org/2020.osact-1.18",
pages = "109--114",
abstract = "As the use of social media platforms increases extensively to freely communicate and share opinions, hate speech becomes an outstanding problem that requires urgent attention. This paper focuses on the problem of detecting hate speech in Arabic tweets. To tackle the problem efficiently, we adopt a {``}quick and simple{''} approach by which we investigate the effectiveness of 15 classical (e.g., SVM) and neural (e.g., CNN) learning models, while exploring two different term representations. Our experiments on 8k labelled dataset show that the best neural learning models outperform the classical ones, while distributed term representation is more effective than statistical bag-of-words representation. Overall, our best classifier (that combines both CNN and RNN in a joint architecture) achieved 0.73 macro-F1 score on the dev set, which significantly outperforms the majority-class baseline that achieves 0.49, proving the effectiveness of our {``}quick and simple{''} approach.",
language = "English",
ISBN = "979-10-95546-51-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abuzayed-elsayed-2020-quick">
<titleInfo>
<title>Quick and Simple Approach for Detecting Hate Speech in Arabic Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abeer</namePart>
<namePart type="family">Abuzayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</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">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resource Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-51-1</identifier>
</relatedItem>
<abstract>As the use of social media platforms increases extensively to freely communicate and share opinions, hate speech becomes an outstanding problem that requires urgent attention. This paper focuses on the problem of detecting hate speech in Arabic tweets. To tackle the problem efficiently, we adopt a “quick and simple” approach by which we investigate the effectiveness of 15 classical (e.g., SVM) and neural (e.g., CNN) learning models, while exploring two different term representations. Our experiments on 8k labelled dataset show that the best neural learning models outperform the classical ones, while distributed term representation is more effective than statistical bag-of-words representation. Overall, our best classifier (that combines both CNN and RNN in a joint architecture) achieved 0.73 macro-F1 score on the dev set, which significantly outperforms the majority-class baseline that achieves 0.49, proving the effectiveness of our “quick and simple” approach.</abstract>
<identifier type="citekey">abuzayed-elsayed-2020-quick</identifier>
<location>
<url>https://aclanthology.org/2020.osact-1.18</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>109</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quick and Simple Approach for Detecting Hate Speech in Arabic Tweets
%A Abuzayed, Abeer
%A Elsayed, Tamer
%Y Al-Khalifa, Hend
%Y Magdy, Walid
%Y Darwish, Kareem
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%S Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection
%D 2020
%8 May
%I European Language Resource Association
%C Marseille, France
%@ 979-10-95546-51-1
%G English
%F abuzayed-elsayed-2020-quick
%X As the use of social media platforms increases extensively to freely communicate and share opinions, hate speech becomes an outstanding problem that requires urgent attention. This paper focuses on the problem of detecting hate speech in Arabic tweets. To tackle the problem efficiently, we adopt a “quick and simple” approach by which we investigate the effectiveness of 15 classical (e.g., SVM) and neural (e.g., CNN) learning models, while exploring two different term representations. Our experiments on 8k labelled dataset show that the best neural learning models outperform the classical ones, while distributed term representation is more effective than statistical bag-of-words representation. Overall, our best classifier (that combines both CNN and RNN in a joint architecture) achieved 0.73 macro-F1 score on the dev set, which significantly outperforms the majority-class baseline that achieves 0.49, proving the effectiveness of our “quick and simple” approach.
%U https://aclanthology.org/2020.osact-1.18
%P 109-114
Markdown (Informal)
[Quick and Simple Approach for Detecting Hate Speech in Arabic Tweets](https://aclanthology.org/2020.osact-1.18) (Abuzayed & Elsayed, OSACT 2020)
ACL