@inproceedings{l-etal-2025-itsallgoodman,
title = "{I}ts{A}ll{G}ood{M}an@{LT}-{EDI}-2025: Fusing {TF}-{IDF} and {M}u{RIL} Embeddings for Detecting Caste and Migration Hate Speech",
author = "L, Amritha Nandini K and
S, Vishal and
R, Giri Prasath and
Thiyagarajan, Anerud 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-1.15/",
pages = "90--94",
ISBN = "978-88-6719-334-9",
abstract = "Caste and migration hate speech detection is a critical task in the context of increasingly multilingual and diverse online discourse. In this work, we address the problem of identifying hate speech targeting caste and migrant communities across a multilingual social media dataset containing Tamil, Tamil written in English script, and English. We explore and compare different feature representations, including TF-IDF vectors and embeddings from pretrained transformer-based models, to train various machine learning classifiers. Our experiments show that a Soft Voting Classifier that make use of both TF-IDF vectors and MuRIL embeddings performs best, achieving a macro F1 score of 0.802 on the test set. This approach was evaluated as part of the Shared Task on Caste and Migration Hate Speech Detection at LT-EDI@LDK 2025, where it ranked 6th overall."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="l-etal-2025-itsallgoodman">
<titleInfo>
<title>ItsAllGoodMan@LT-EDI-2025: Fusing TF-IDF and MuRIL Embeddings for Detecting Caste and Migration Hate Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amritha</namePart>
<namePart type="given">Nandini</namePart>
<namePart type="given">K</namePart>
<namePart type="family">L</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishal</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giri</namePart>
<namePart type="given">Prasath</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anerud</namePart>
<namePart type="family">Thiyagarajan</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>Caste and migration hate speech detection is a critical task in the context of increasingly multilingual and diverse online discourse. In this work, we address the problem of identifying hate speech targeting caste and migrant communities across a multilingual social media dataset containing Tamil, Tamil written in English script, and English. We explore and compare different feature representations, including TF-IDF vectors and embeddings from pretrained transformer-based models, to train various machine learning classifiers. Our experiments show that a Soft Voting Classifier that make use of both TF-IDF vectors and MuRIL embeddings performs best, achieving a macro F1 score of 0.802 on the test set. This approach was evaluated as part of the Shared Task on Caste and Migration Hate Speech Detection at LT-EDI@LDK 2025, where it ranked 6th overall.</abstract>
<identifier type="citekey">l-etal-2025-itsallgoodman</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.15/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>90</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ItsAllGoodMan@LT-EDI-2025: Fusing TF-IDF and MuRIL Embeddings for Detecting Caste and Migration Hate Speech
%A L, Amritha Nandini K.
%A S, Vishal
%A R, Giri Prasath
%A Thiyagarajan, Anerud
%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 l-etal-2025-itsallgoodman
%X Caste and migration hate speech detection is a critical task in the context of increasingly multilingual and diverse online discourse. In this work, we address the problem of identifying hate speech targeting caste and migrant communities across a multilingual social media dataset containing Tamil, Tamil written in English script, and English. We explore and compare different feature representations, including TF-IDF vectors and embeddings from pretrained transformer-based models, to train various machine learning classifiers. Our experiments show that a Soft Voting Classifier that make use of both TF-IDF vectors and MuRIL embeddings performs best, achieving a macro F1 score of 0.802 on the test set. This approach was evaluated as part of the Shared Task on Caste and Migration Hate Speech Detection at LT-EDI@LDK 2025, where it ranked 6th overall.
%U https://aclanthology.org/2025.ltedi-1.15/
%P 90-94
Markdown (Informal)
[ItsAllGoodMan@LT-EDI-2025: Fusing TF-IDF and MuRIL Embeddings for Detecting Caste and Migration Hate Speech](https://aclanthology.org/2025.ltedi-1.15/) (L et al., LTEDI 2025)
ACL
- Amritha Nandini K L, Vishal S, Giri Prasath R, Anerud Thiyagarajan, and Sachin Kumar S. 2025. ItsAllGoodMan@LT-EDI-2025: Fusing TF-IDF and MuRIL Embeddings for Detecting Caste and Migration Hate Speech. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 90–94, Naples, Italy. Unior Press.