@inproceedings{subramanian-etal-2025-kec,
title = "{KEC}{\_}{TECH}{\_}{TITANS}@{D}ravidian{L}ang{T}ech 2025: Abusive Text Detection in {T}amil and {M}alayalam Social Media Comments Using Machine Learning",
author = "Subramanian, Malliga and
Shanmugavadivel, Kogilavani and
P, Deepiga and
S, Dharshini and
S, Ananthakumar and
C, Praveenkumar",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.45/",
doi = "10.18653/v1/2025.dravidianlangtech-1.45",
pages = "259--263",
ISBN = "979-8-89176-228-2",
abstract = "Social media platforms have become a breeding ground for hostility and toxicity, with abusive language targeting women becoming a pervasive issue. This paper addresses the detection of abusive content in Tamil and Malayalam social media comments using machine learning models. We experimented with GRU, LSTM, Bidirectional LSTM, CNN, FastText, and XGBoost models, evaluating their performance on a code-mixed dataset of Tamil and Malayalam comments collected from YouTube. Our findings demonstrate that FastText and CNN models yielded the best performance among the evaluated classifiers, achieving F1-scores of 0.73 each. This study contributes to the ongoing research on abusive text detection for under-resourced languages and highlights the need for robust, scalable solutions to combat online toxicity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="subramanian-etal-2025-kec">
<titleInfo>
<title>KEC_TECH_TITANS@DravidianLangTech 2025: Abusive Text Detection in Tamil and Malayalam Social Media Comments Using Machine Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kogilavani</namePart>
<namePart type="family">Shanmugavadivel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepiga</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dharshini</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananthakumar</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praveenkumar</namePart>
<namePart type="family">C</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth 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">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>Social media platforms have become a breeding ground for hostility and toxicity, with abusive language targeting women becoming a pervasive issue. This paper addresses the detection of abusive content in Tamil and Malayalam social media comments using machine learning models. We experimented with GRU, LSTM, Bidirectional LSTM, CNN, FastText, and XGBoost models, evaluating their performance on a code-mixed dataset of Tamil and Malayalam comments collected from YouTube. Our findings demonstrate that FastText and CNN models yielded the best performance among the evaluated classifiers, achieving F1-scores of 0.73 each. This study contributes to the ongoing research on abusive text detection for under-resourced languages and highlights the need for robust, scalable solutions to combat online toxicity.</abstract>
<identifier type="citekey">subramanian-etal-2025-kec</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.45</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.45/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>259</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KEC_TECH_TITANS@DravidianLangTech 2025: Abusive Text Detection in Tamil and Malayalam Social Media Comments Using Machine Learning
%A Subramanian, Malliga
%A Shanmugavadivel, Kogilavani
%A P, Deepiga
%A S, Dharshini
%A S, Ananthakumar
%A C, Praveenkumar
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F subramanian-etal-2025-kec
%X Social media platforms have become a breeding ground for hostility and toxicity, with abusive language targeting women becoming a pervasive issue. This paper addresses the detection of abusive content in Tamil and Malayalam social media comments using machine learning models. We experimented with GRU, LSTM, Bidirectional LSTM, CNN, FastText, and XGBoost models, evaluating their performance on a code-mixed dataset of Tamil and Malayalam comments collected from YouTube. Our findings demonstrate that FastText and CNN models yielded the best performance among the evaluated classifiers, achieving F1-scores of 0.73 each. This study contributes to the ongoing research on abusive text detection for under-resourced languages and highlights the need for robust, scalable solutions to combat online toxicity.
%R 10.18653/v1/2025.dravidianlangtech-1.45
%U https://aclanthology.org/2025.dravidianlangtech-1.45/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.45
%P 259-263
Markdown (Informal)
[KEC_TECH_TITANS@DravidianLangTech 2025: Abusive Text Detection in Tamil and Malayalam Social Media Comments Using Machine Learning](https://aclanthology.org/2025.dravidianlangtech-1.45/) (Subramanian et al., DravidianLangTech 2025)
ACL
- Malliga Subramanian, Kogilavani Shanmugavadivel, Deepiga P, Dharshini S, Ananthakumar S, and Praveenkumar C. 2025. KEC_TECH_TITANS@DravidianLangTech 2025: Abusive Text Detection in Tamil and Malayalam Social Media Comments Using Machine Learning. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 259–263, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.