@inproceedings{guellil-etal-2024-annotators,
title = "The Annotators Agree to Not Agree on the Fine-grained Annotation of Hate-speech against Women in {A}lgerian Dialect Comments",
author = "Guellil, Imane and
Houichi, Yousra and
Chennoufi, Sara and
Boubred, Mohamed and
Boucetta, Anfal Yousra and
Azouaou, Faical",
editor = "Mabuya, Rooweither and
Matfunjwa, Muzi and
Setaka, Mmasibidi and
van Zaanen, Menno",
booktitle = "Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.rail-1.15",
pages = "133--139",
abstract = "A significant number of research studies have been presented for detecting hate speech in social media during the last few years. However, the majority of these studies are in English. Only a few studies focus on Arabic and its dialects (especially the Algerian dialect) with a smaller number of them targeting sexism detection (or hate speech against women). Even the works that have been proposed on Arabic sexism detection consider two classes only (hateful and non-hateful), and three classes(adding the neutral class) in the best scenario. This paper aims to propose the first fine-grained corpus focusing on 13 classes. However, given the challenges related to hate speech and fine-grained annotation, the Kappa metric is relatively low among the annotators (i.e. 35{\%} ). This work in progress proposes three main contributions: 1) Annotation of different categories related to hate speech such as insults, vulgar words or hate in general. 2) Annotation of 10,000 comments, in Arabic and Algerian dialects, automatically extracted from Youtube. 3) High-lighting the challenges related to manual annotation such as subjectivity, risk of bias, lack of annotation guidelines, etc",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guellil-etal-2024-annotators">
<titleInfo>
<title>The Annotators Agree to Not Agree on the Fine-grained Annotation of Hate-speech against Women in Algerian Dialect Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imane</namePart>
<namePart type="family">Guellil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousra</namePart>
<namePart type="family">Houichi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Chennoufi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Boubred</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anfal</namePart>
<namePart type="given">Yousra</namePart>
<namePart type="family">Boucetta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faical</namePart>
<namePart type="family">Azouaou</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 Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muzi</namePart>
<namePart type="family">Matfunjwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Menno</namePart>
<namePart type="family">van Zaanen</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>A significant number of research studies have been presented for detecting hate speech in social media during the last few years. However, the majority of these studies are in English. Only a few studies focus on Arabic and its dialects (especially the Algerian dialect) with a smaller number of them targeting sexism detection (or hate speech against women). Even the works that have been proposed on Arabic sexism detection consider two classes only (hateful and non-hateful), and three classes(adding the neutral class) in the best scenario. This paper aims to propose the first fine-grained corpus focusing on 13 classes. However, given the challenges related to hate speech and fine-grained annotation, the Kappa metric is relatively low among the annotators (i.e. 35% ). This work in progress proposes three main contributions: 1) Annotation of different categories related to hate speech such as insults, vulgar words or hate in general. 2) Annotation of 10,000 comments, in Arabic and Algerian dialects, automatically extracted from Youtube. 3) High-lighting the challenges related to manual annotation such as subjectivity, risk of bias, lack of annotation guidelines, etc</abstract>
<identifier type="citekey">guellil-etal-2024-annotators</identifier>
<location>
<url>https://aclanthology.org/2024.rail-1.15</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>133</start>
<end>139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Annotators Agree to Not Agree on the Fine-grained Annotation of Hate-speech against Women in Algerian Dialect Comments
%A Guellil, Imane
%A Houichi, Yousra
%A Chennoufi, Sara
%A Boubred, Mohamed
%A Boucetta, Anfal Yousra
%A Azouaou, Faical
%Y Mabuya, Rooweither
%Y Matfunjwa, Muzi
%Y Setaka, Mmasibidi
%Y van Zaanen, Menno
%S Proceedings of the Fifth Workshop on Resources for African Indigenous Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F guellil-etal-2024-annotators
%X A significant number of research studies have been presented for detecting hate speech in social media during the last few years. However, the majority of these studies are in English. Only a few studies focus on Arabic and its dialects (especially the Algerian dialect) with a smaller number of them targeting sexism detection (or hate speech against women). Even the works that have been proposed on Arabic sexism detection consider two classes only (hateful and non-hateful), and three classes(adding the neutral class) in the best scenario. This paper aims to propose the first fine-grained corpus focusing on 13 classes. However, given the challenges related to hate speech and fine-grained annotation, the Kappa metric is relatively low among the annotators (i.e. 35% ). This work in progress proposes three main contributions: 1) Annotation of different categories related to hate speech such as insults, vulgar words or hate in general. 2) Annotation of 10,000 comments, in Arabic and Algerian dialects, automatically extracted from Youtube. 3) High-lighting the challenges related to manual annotation such as subjectivity, risk of bias, lack of annotation guidelines, etc
%U https://aclanthology.org/2024.rail-1.15
%P 133-139
Markdown (Informal)
[The Annotators Agree to Not Agree on the Fine-grained Annotation of Hate-speech against Women in Algerian Dialect Comments](https://aclanthology.org/2024.rail-1.15) (Guellil et al., RAIL-WS 2024)
ACL