@inproceedings{amin-etal-2025-hinterwelt,
title = "Hinterwelt@{LT}-{EDI} 2025: A Transformer-Based Detection of Caste and Migration Hate Speech in {T}amil Social Media",
author = "Amin, Md. Al and
Aftahee, Sabik and
Rahman, Md. Abdur and
Khan, Md. Sajid Hossain and
Rahman, Md. Ashiqur",
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-1.24/",
pages = "140--145",
ISBN = "978-88-6719-334-9",
abstract = "This paper presents our system for detecting caste and migration-related hate speech in Tamil social media comments, addressing the challenges in this low-resource language setting. We experimented with multiple approaches on a dataset of 7,875 annotated comments. Our methodology encompasses traditional machine learning classifiers (SVM, Random Forest, KNN), deep learning models (CNN, CNN-BiLSTM), and transformer-based architectures (MuRIL, IndicBERT, XLM-RoBERTa). Comprehensive evaluations demonstrate that transformer-based models substantially outperform traditional approaches, with MuRIL-large achieving the highest performance with a macro F1 score of 0.8092. Error analysis reveals challenges in detecting implicit and culturally-specific hate speech expressions requiring deeper socio-cultural context. Our team ranked 5th in the LT-EDI@LDK 2025 shared task with an F1 score of 0.80916. This work contributes to combating harmful online content in low-resource languages and highlights the effectiveness of large pre-trained multilingual models for nuanced text classification tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amin-etal-2025-hinterwelt">
<titleInfo>
<title>Hinterwelt@LT-EDI 2025: A Transformer-Based Detection of Caste and Migration Hate Speech in Tamil Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabik</namePart>
<namePart type="family">Aftahee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Abdur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Sajid</namePart>
<namePart type="given">Hossain</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Ashiqur</namePart>
<namePart type="family">Rahman</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>This paper presents our system for detecting caste and migration-related hate speech in Tamil social media comments, addressing the challenges in this low-resource language setting. We experimented with multiple approaches on a dataset of 7,875 annotated comments. Our methodology encompasses traditional machine learning classifiers (SVM, Random Forest, KNN), deep learning models (CNN, CNN-BiLSTM), and transformer-based architectures (MuRIL, IndicBERT, XLM-RoBERTa). Comprehensive evaluations demonstrate that transformer-based models substantially outperform traditional approaches, with MuRIL-large achieving the highest performance with a macro F1 score of 0.8092. Error analysis reveals challenges in detecting implicit and culturally-specific hate speech expressions requiring deeper socio-cultural context. Our team ranked 5th in the LT-EDI@LDK 2025 shared task with an F1 score of 0.80916. This work contributes to combating harmful online content in low-resource languages and highlights the effectiveness of large pre-trained multilingual models for nuanced text classification tasks.</abstract>
<identifier type="citekey">amin-etal-2025-hinterwelt</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.24/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>140</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hinterwelt@LT-EDI 2025: A Transformer-Based Detection of Caste and Migration Hate Speech in Tamil Social Media
%A Amin, Md. Al
%A Aftahee, Sabik
%A Rahman, Md. Abdur
%A Khan, Md. Sajid Hossain
%A Rahman, Md. Ashiqur
%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 amin-etal-2025-hinterwelt
%X This paper presents our system for detecting caste and migration-related hate speech in Tamil social media comments, addressing the challenges in this low-resource language setting. We experimented with multiple approaches on a dataset of 7,875 annotated comments. Our methodology encompasses traditional machine learning classifiers (SVM, Random Forest, KNN), deep learning models (CNN, CNN-BiLSTM), and transformer-based architectures (MuRIL, IndicBERT, XLM-RoBERTa). Comprehensive evaluations demonstrate that transformer-based models substantially outperform traditional approaches, with MuRIL-large achieving the highest performance with a macro F1 score of 0.8092. Error analysis reveals challenges in detecting implicit and culturally-specific hate speech expressions requiring deeper socio-cultural context. Our team ranked 5th in the LT-EDI@LDK 2025 shared task with an F1 score of 0.80916. This work contributes to combating harmful online content in low-resource languages and highlights the effectiveness of large pre-trained multilingual models for nuanced text classification tasks.
%U https://aclanthology.org/2025.ltedi-1.24/
%P 140-145
Markdown (Informal)
[Hinterwelt@LT-EDI 2025: A Transformer-Based Detection of Caste and Migration Hate Speech in Tamil Social Media](https://aclanthology.org/2025.ltedi-1.24/) (Amin et al., LTEDI 2025)
ACL
- Md. Al Amin, Sabik Aftahee, Md. Abdur Rahman, Md. Sajid Hossain Khan, and Md. Ashiqur Rahman. 2025. Hinterwelt@LT-EDI 2025: A Transformer-Based Detection of Caste and Migration Hate Speech in Tamil Social Media. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 140–145, Naples, Italy. Unior Press.