@inproceedings{beyhan-etal-2022-turkish,
title = "A {T}urkish Hate Speech Dataset and Detection System",
author = "Beyhan, Fatih and
{\c{C}}ar{\i}k, Buse and
Ar{\i}n, {\.I}nan{\c{c}} and
Terzio{\u{g}}lu, Ay{\c{s}}ecan and
Yanikoglu, Berrin and
Yeniterzi, Reyyan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.443",
pages = "4177--4185",
abstract = "Social media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We first adopted a definition for hate speech that is in line with our goals and amenable to easy annotation; then designed the annotation schema for annotating the collected tweets. The Istanbul Convention dataset consists of tweets posted following the withdrawal of Turkey from the Istanbul Convention. The Refugees dataset was created by collecting tweets about immigrants by filtering based on commonly used keywords related to immigrants. Finally, we have developed a hate speech detection system using the transformer architecture (BERTurk), to be used as a baseline for the collected dataset. The binary classification accuracy is 77{\%} when the system is evaluated using 5-fold cross-validation on the Istanbul Convention dataset and 71{\%} for the Refugee dataset. We also tested a regression model with 0.66 and 0.83 RMSE on a scale of [0-4], for the Istanbul Convention and Refugees datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beyhan-etal-2022-turkish">
<titleInfo>
<title>A Turkish Hate Speech Dataset and Detection System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatih</namePart>
<namePart type="family">Beyhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Buse</namePart>
<namePart type="family">Çarık</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">İnanç</namePart>
<namePart type="family">Arın</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayşecan</namePart>
<namePart type="family">Terzioğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berrin</namePart>
<namePart type="family">Yanikoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reyyan</namePart>
<namePart type="family">Yeniterzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We first adopted a definition for hate speech that is in line with our goals and amenable to easy annotation; then designed the annotation schema for annotating the collected tweets. The Istanbul Convention dataset consists of tweets posted following the withdrawal of Turkey from the Istanbul Convention. The Refugees dataset was created by collecting tweets about immigrants by filtering based on commonly used keywords related to immigrants. Finally, we have developed a hate speech detection system using the transformer architecture (BERTurk), to be used as a baseline for the collected dataset. The binary classification accuracy is 77% when the system is evaluated using 5-fold cross-validation on the Istanbul Convention dataset and 71% for the Refugee dataset. We also tested a regression model with 0.66 and 0.83 RMSE on a scale of [0-4], for the Istanbul Convention and Refugees datasets.</abstract>
<identifier type="citekey">beyhan-etal-2022-turkish</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.443</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4177</start>
<end>4185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Turkish Hate Speech Dataset and Detection System
%A Beyhan, Fatih
%A Çarık, Buse
%A Arın, İnanç
%A Terzioğlu, Ayşecan
%A Yanikoglu, Berrin
%A Yeniterzi, Reyyan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F beyhan-etal-2022-turkish
%X Social media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We first adopted a definition for hate speech that is in line with our goals and amenable to easy annotation; then designed the annotation schema for annotating the collected tweets. The Istanbul Convention dataset consists of tweets posted following the withdrawal of Turkey from the Istanbul Convention. The Refugees dataset was created by collecting tweets about immigrants by filtering based on commonly used keywords related to immigrants. Finally, we have developed a hate speech detection system using the transformer architecture (BERTurk), to be used as a baseline for the collected dataset. The binary classification accuracy is 77% when the system is evaluated using 5-fold cross-validation on the Istanbul Convention dataset and 71% for the Refugee dataset. We also tested a regression model with 0.66 and 0.83 RMSE on a scale of [0-4], for the Istanbul Convention and Refugees datasets.
%U https://aclanthology.org/2022.lrec-1.443
%P 4177-4185
Markdown (Informal)
[A Turkish Hate Speech Dataset and Detection System](https://aclanthology.org/2022.lrec-1.443) (Beyhan et al., LREC 2022)
ACL
- Fatih Beyhan, Buse Çarık, İnanç Arın, Ayşecan Terzioğlu, Berrin Yanikoglu, and Reyyan Yeniterzi. 2022. A Turkish Hate Speech Dataset and Detection System. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4177–4185, Marseille, France. European Language Resources Association.