@inproceedings{sai-etal-2024-iiitdwd,
title = "{IIITDWD}{\_}{SVC}@{D}ravidian{L}ang{T}ech-2024: Breaking Language Barriers; Hate Speech Detection in {T}elugu-{E}nglish Code-Mixed Text",
author = "Sai, Chava and
Kumar, Rangoori and
Saumya, Sunil and
Biradar, Shankar",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Nadarajan, Rajeswari and
Ravikiran, Manikandan",
booktitle = "Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.dravidianlangtech-1.19",
pages = "119--123",
abstract = "Social media platforms have become increasingly popular and are utilized for a wide range of purposes, including product promotion, news sharing, accomplishment sharing, and much more. However, it is also employed for defamatory speech, intimidation, and the propagation of untruths about particular groups of people. Further, hateful and offensive posts spread quickly and often have a negative impact on people; it is important to identify and remove them from social media platforms as soon as possible. Over the past few years, research on hate speech detection and offensive content has grown in popularity. One of the many difficulties in identifying hate speech on social media platforms is the use of code-mixed language. The majority of people who use social media typically share their messages in languages with mixed codes, like Telugu{--}English. To encourage research in this direction, the organizers of DravidianLangTech@EACL-2024 conducted a shared task to identify hateful content in Telugu-English code-mixed text. Our team participated in this shared task, employing three different models: Xlm-Roberta, BERT, and Hate-BERT. In particular, our BERT-based model secured the 14th rank in the competition with a macro F1 score of 0.65.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sai-etal-2024-iiitdwd">
<titleInfo>
<title>IIITDWD_SVC@DravidianLangTech-2024: Breaking Language Barriers; Hate Speech Detection in Telugu-English Code-Mixed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chava</namePart>
<namePart type="family">Sai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rangoori</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Saumya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shankar</namePart>
<namePart type="family">Biradar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajeswari</namePart>
<namePart type="family">Nadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media platforms have become increasingly popular and are utilized for a wide range of purposes, including product promotion, news sharing, accomplishment sharing, and much more. However, it is also employed for defamatory speech, intimidation, and the propagation of untruths about particular groups of people. Further, hateful and offensive posts spread quickly and often have a negative impact on people; it is important to identify and remove them from social media platforms as soon as possible. Over the past few years, research on hate speech detection and offensive content has grown in popularity. One of the many difficulties in identifying hate speech on social media platforms is the use of code-mixed language. The majority of people who use social media typically share their messages in languages with mixed codes, like Telugu–English. To encourage research in this direction, the organizers of DravidianLangTech@EACL-2024 conducted a shared task to identify hateful content in Telugu-English code-mixed text. Our team participated in this shared task, employing three different models: Xlm-Roberta, BERT, and Hate-BERT. In particular, our BERT-based model secured the 14th rank in the competition with a macro F1 score of 0.65.</abstract>
<identifier type="citekey">sai-etal-2024-iiitdwd</identifier>
<location>
<url>https://aclanthology.org/2024.dravidianlangtech-1.19</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>119</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IIITDWD_SVC@DravidianLangTech-2024: Breaking Language Barriers; Hate Speech Detection in Telugu-English Code-Mixed Text
%A Sai, Chava
%A Kumar, Rangoori
%A Saumya, Sunil
%A Biradar, Shankar
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Nadarajan, Rajeswari
%Y Ravikiran, Manikandan
%S Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F sai-etal-2024-iiitdwd
%X Social media platforms have become increasingly popular and are utilized for a wide range of purposes, including product promotion, news sharing, accomplishment sharing, and much more. However, it is also employed for defamatory speech, intimidation, and the propagation of untruths about particular groups of people. Further, hateful and offensive posts spread quickly and often have a negative impact on people; it is important to identify and remove them from social media platforms as soon as possible. Over the past few years, research on hate speech detection and offensive content has grown in popularity. One of the many difficulties in identifying hate speech on social media platforms is the use of code-mixed language. The majority of people who use social media typically share their messages in languages with mixed codes, like Telugu–English. To encourage research in this direction, the organizers of DravidianLangTech@EACL-2024 conducted a shared task to identify hateful content in Telugu-English code-mixed text. Our team participated in this shared task, employing three different models: Xlm-Roberta, BERT, and Hate-BERT. In particular, our BERT-based model secured the 14th rank in the competition with a macro F1 score of 0.65.
%U https://aclanthology.org/2024.dravidianlangtech-1.19
%P 119-123
Markdown (Informal)
[IIITDWD_SVC@DravidianLangTech-2024: Breaking Language Barriers; Hate Speech Detection in Telugu-English Code-Mixed Text](https://aclanthology.org/2024.dravidianlangtech-1.19) (Sai et al., DravidianLangTech-WS 2024)
ACL