@inproceedings{alshaalan-al-khalifa-2020-hate,
title = "Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach",
author = "Alshaalan, Raghad and
Al-Khalifa, Hend",
editor = "Zitouni, Imed and
Abdul-Mageed, Muhammad and
Bouamor, Houda and
Bougares, Fethi and
El-Haj, Mahmoud and
Tomeh, Nadi and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fifth Arabic Natural Language Processing Workshop",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wanlp-1.2",
pages = "12--23",
abstract = "With the rise of hate speech phenomena in Twittersphere, significant research efforts have been undertaken to provide automatic solutions for detecting hate speech, varying from simple ma-chine learning models to more complex deep neural network models. Despite that, research works investigating hate speech problem in Arabic are still limited. This paper, therefore, aims to investigate several neural network models based on Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN) to detect hate speech in Arabic tweets. It also evaluates the recent language representation model BERT on the task of Arabic hate speech detection. To conduct our experiments, we firstly built a new hate speech dataset that contains 9,316 annotated tweets. Then, we conducted a set of experiments on two datasets to evaluate four models: CNN, GRU, CNN+GRU and BERT. Our experimental results on our dataset and an out-domain dataset show that CNN model gives the best performance with an F1-score of 0.79 and AUROC of 0.89.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshaalan-al-khalifa-2020-hate">
<titleInfo>
<title>Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raghad</namePart>
<namePart type="family">Alshaalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<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">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</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">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</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">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the rise of hate speech phenomena in Twittersphere, significant research efforts have been undertaken to provide automatic solutions for detecting hate speech, varying from simple ma-chine learning models to more complex deep neural network models. Despite that, research works investigating hate speech problem in Arabic are still limited. This paper, therefore, aims to investigate several neural network models based on Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN) to detect hate speech in Arabic tweets. It also evaluates the recent language representation model BERT on the task of Arabic hate speech detection. To conduct our experiments, we firstly built a new hate speech dataset that contains 9,316 annotated tweets. Then, we conducted a set of experiments on two datasets to evaluate four models: CNN, GRU, CNN+GRU and BERT. Our experimental results on our dataset and an out-domain dataset show that CNN model gives the best performance with an F1-score of 0.79 and AUROC of 0.89.</abstract>
<identifier type="citekey">alshaalan-al-khalifa-2020-hate</identifier>
<location>
<url>https://aclanthology.org/2020.wanlp-1.2</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>12</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach
%A Alshaalan, Raghad
%A Al-Khalifa, Hend
%Y Zitouni, Imed
%Y Abdul-Mageed, Muhammad
%Y Bouamor, Houda
%Y Bougares, Fethi
%Y El-Haj, Mahmoud
%Y Tomeh, Nadi
%Y Zaghouani, Wajdi
%S Proceedings of the Fifth Arabic Natural Language Processing Workshop
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F alshaalan-al-khalifa-2020-hate
%X With the rise of hate speech phenomena in Twittersphere, significant research efforts have been undertaken to provide automatic solutions for detecting hate speech, varying from simple ma-chine learning models to more complex deep neural network models. Despite that, research works investigating hate speech problem in Arabic are still limited. This paper, therefore, aims to investigate several neural network models based on Convolutional Neural Network (CNN) and Recurrent Neural Networks (RNN) to detect hate speech in Arabic tweets. It also evaluates the recent language representation model BERT on the task of Arabic hate speech detection. To conduct our experiments, we firstly built a new hate speech dataset that contains 9,316 annotated tweets. Then, we conducted a set of experiments on two datasets to evaluate four models: CNN, GRU, CNN+GRU and BERT. Our experimental results on our dataset and an out-domain dataset show that CNN model gives the best performance with an F1-score of 0.79 and AUROC of 0.89.
%U https://aclanthology.org/2020.wanlp-1.2
%P 12-23
Markdown (Informal)
[Hate Speech Detection in Saudi Twittersphere: A Deep Learning Approach](https://aclanthology.org/2020.wanlp-1.2) (Alshaalan & Al-Khalifa, WANLP 2020)
ACL