@inproceedings{buyukdemirci-etal-2024-jl,
title = "{JL}-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection",
author = {B{\"u}y{\"u}kdemirci, Kaan and
Kucukkaya, Izzet Emre and
{\"O}lmez, Eren and
Toraman, Cagri},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.834",
pages = "9543--9553",
abstract = "The detection of hate speech is a subject extensively explored by researchers, and machine learning algorithms play a crucial role in this domain. The existing resources mostly focus on text sequence classification for the task of hate speech detection. However, the target of hateful content is another dimension that has not been studied in details due to the lack of data resources. In this study, we address this gap by introducing a novel tweet dataset for the task of joint learning of hate speech detection and target detection, called JL-Hate, for the tasks of sequential text classification and token classification, respectively. The JL-Hate dataset consists of 1,530 tweets divided equally in English and Turkish languages. Leveraging this dataset, we conduct a series of benchmark experiments. We utilize a joint learning model to concurrently perform sequence and token classification tasks on our data. Our experimental results demonstrate consistent performance with the prevalent studies, both in sequence and token classification tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buyukdemirci-etal-2024-jl">
<titleInfo>
<title>JL-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaan</namePart>
<namePart type="family">Büyükdemirci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izzet</namePart>
<namePart type="given">Emre</namePart>
<namePart type="family">Kucukkaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eren</namePart>
<namePart type="family">Ölmez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cagri</namePart>
<namePart type="family">Toraman</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 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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>The detection of hate speech is a subject extensively explored by researchers, and machine learning algorithms play a crucial role in this domain. The existing resources mostly focus on text sequence classification for the task of hate speech detection. However, the target of hateful content is another dimension that has not been studied in details due to the lack of data resources. In this study, we address this gap by introducing a novel tweet dataset for the task of joint learning of hate speech detection and target detection, called JL-Hate, for the tasks of sequential text classification and token classification, respectively. The JL-Hate dataset consists of 1,530 tweets divided equally in English and Turkish languages. Leveraging this dataset, we conduct a series of benchmark experiments. We utilize a joint learning model to concurrently perform sequence and token classification tasks on our data. Our experimental results demonstrate consistent performance with the prevalent studies, both in sequence and token classification tasks.</abstract>
<identifier type="citekey">buyukdemirci-etal-2024-jl</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.834</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9543</start>
<end>9553</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JL-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection
%A Büyükdemirci, Kaan
%A Kucukkaya, Izzet Emre
%A Ölmez, Eren
%A Toraman, Cagri
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F buyukdemirci-etal-2024-jl
%X The detection of hate speech is a subject extensively explored by researchers, and machine learning algorithms play a crucial role in this domain. The existing resources mostly focus on text sequence classification for the task of hate speech detection. However, the target of hateful content is another dimension that has not been studied in details due to the lack of data resources. In this study, we address this gap by introducing a novel tweet dataset for the task of joint learning of hate speech detection and target detection, called JL-Hate, for the tasks of sequential text classification and token classification, respectively. The JL-Hate dataset consists of 1,530 tweets divided equally in English and Turkish languages. Leveraging this dataset, we conduct a series of benchmark experiments. We utilize a joint learning model to concurrently perform sequence and token classification tasks on our data. Our experimental results demonstrate consistent performance with the prevalent studies, both in sequence and token classification tasks.
%U https://aclanthology.org/2024.lrec-main.834
%P 9543-9553
Markdown (Informal)
[JL-Hate: An Annotated Dataset for Joint Learning of Hate Speech and Target Detection](https://aclanthology.org/2024.lrec-main.834) (Büyükdemirci et al., LREC-COLING 2024)
ACL