@inproceedings{s-etal-2025-ns,
title = "{NS}@{LT}-{EDI}-2025 {C}aste{M}igration based hate speech Detection",
author = "S, Nishanth and
Rengarajan, Shruthi and
S, Sachin Kumar",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.13/",
pages = "80--83",
ISBN = "978-88-6719-334-9",
abstract = "Hate speech directed at caste and migrant communities is a widespread problem on social media, frequently taking the form of insults specific to a given region, coded language, and disparaging slurs. This type of abuse seriously jeopardizes both individual well-being and social harmony in addition to perpetuating discrimination. In order to promote safer and more inclusive digital environments, it is imperative that this challenge be addressed. However, linguistic subtleties, code-mixing, and the lack of extensive annotated datasets make it difficult to detect such hate speech in Indian languages like Tamil. We suggest a supervised machine learning system that uses FastText embeddings specifically designed for Tamil-language content and Whisper-based speech recognition to address these issues. This strategy aims to precisely identify hate speech connected to caste and migration, supporting the larger endeavor to reduce online abuse in low resource languages like Tamil."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-etal-2025-ns">
<titleInfo>
<title>NS@LT-EDI-2025 CasteMigration based hate speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nishanth</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruthi</namePart>
<namePart type="family">Rengarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>Hate speech directed at caste and migrant communities is a widespread problem on social media, frequently taking the form of insults specific to a given region, coded language, and disparaging slurs. This type of abuse seriously jeopardizes both individual well-being and social harmony in addition to perpetuating discrimination. In order to promote safer and more inclusive digital environments, it is imperative that this challenge be addressed. However, linguistic subtleties, code-mixing, and the lack of extensive annotated datasets make it difficult to detect such hate speech in Indian languages like Tamil. We suggest a supervised machine learning system that uses FastText embeddings specifically designed for Tamil-language content and Whisper-based speech recognition to address these issues. This strategy aims to precisely identify hate speech connected to caste and migration, supporting the larger endeavor to reduce online abuse in low resource languages like Tamil.</abstract>
<identifier type="citekey">s-etal-2025-ns</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.13/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>80</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NS@LT-EDI-2025 CasteMigration based hate speech Detection
%A S, Nishanth
%A Rengarajan, Shruthi
%A S, Sachin Kumar
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F s-etal-2025-ns
%X Hate speech directed at caste and migrant communities is a widespread problem on social media, frequently taking the form of insults specific to a given region, coded language, and disparaging slurs. This type of abuse seriously jeopardizes both individual well-being and social harmony in addition to perpetuating discrimination. In order to promote safer and more inclusive digital environments, it is imperative that this challenge be addressed. However, linguistic subtleties, code-mixing, and the lack of extensive annotated datasets make it difficult to detect such hate speech in Indian languages like Tamil. We suggest a supervised machine learning system that uses FastText embeddings specifically designed for Tamil-language content and Whisper-based speech recognition to address these issues. This strategy aims to precisely identify hate speech connected to caste and migration, supporting the larger endeavor to reduce online abuse in low resource languages like Tamil.
%U https://aclanthology.org/2025.ltedi-1.13/
%P 80-83
Markdown (Informal)
[NS@LT-EDI-2025 CasteMigration based hate speech Detection](https://aclanthology.org/2025.ltedi-1.13/) (S et al., LTEDI 2025)
ACL
- Nishanth S, Shruthi Rengarajan, and Sachin Kumar S. 2025. NS@LT-EDI-2025 CasteMigration based hate speech Detection. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 80–83, Naples, Italy. Unior Press.