@inproceedings{naib-etal-2025-cuetraptors,
title = "cuet{R}aptors@{D}ravidian{L}ang{T}ech 2025: Transformer-Based Approaches for Detecting Abusive {T}amil Text Targeting Women on Social Media",
author = "Naib, Md. Mubasshir and
Shohag, Md. Saikat Hossain and
Hossain, Alamgir and
Hossain, Jawad and
Hoque, Mohammed Moshiul",
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-1.125/",
doi = "10.18653/v1/2025.dravidianlangtech-1.125",
pages = "739--745",
ISBN = "979-8-89176-228-2",
abstract = "With the exponential growth of social media usage, the prevalence of abusive language targeting women has become a pressing issue, particularly in low-resource languages (LRLs) like Tamil and Malayalam. This study is part of the shared task at DravidianLangTech@NAACL 2025, which focuses on detecting abusive comments in Tamil social media content. The provided dataset consists of binary-labeled comments (Abusive or Non-Abusive), gathered from YouTube, reflecting explicit abuse, implicit bias, stereotypes, and coded language. We developed and evaluated multiple models for this task, including traditional machine learning algorithms (Logistic Regression, Support Vector Machine, Random Forest Classifier, and Multinomial Naive Bayes), deep learning models (CNN, BiLSTM, and CNN+BiLSTM), and transformer-based architectures (DistilBERT, Multilingual BERT, XLM-RoBERTa), and fine-tuned variants of these models. Our best-performing model, Multilingual BERT, achieved a weighted F1-score of 0.7203, ranking 19 in the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naib-etal-2025-cuetraptors">
<titleInfo>
<title>cuetRaptors@DravidianLangTech 2025: Transformer-Based Approaches for Detecting Abusive Tamil Text Targeting Women on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mubasshir</namePart>
<namePart type="family">Naib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Saikat</namePart>
<namePart type="given">Hossain</namePart>
<namePart type="family">Shohag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alamgir</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jawad</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</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>With the exponential growth of social media usage, the prevalence of abusive language targeting women has become a pressing issue, particularly in low-resource languages (LRLs) like Tamil and Malayalam. This study is part of the shared task at DravidianLangTech@NAACL 2025, which focuses on detecting abusive comments in Tamil social media content. The provided dataset consists of binary-labeled comments (Abusive or Non-Abusive), gathered from YouTube, reflecting explicit abuse, implicit bias, stereotypes, and coded language. We developed and evaluated multiple models for this task, including traditional machine learning algorithms (Logistic Regression, Support Vector Machine, Random Forest Classifier, and Multinomial Naive Bayes), deep learning models (CNN, BiLSTM, and CNN+BiLSTM), and transformer-based architectures (DistilBERT, Multilingual BERT, XLM-RoBERTa), and fine-tuned variants of these models. Our best-performing model, Multilingual BERT, achieved a weighted F1-score of 0.7203, ranking 19 in the competition.</abstract>
<identifier type="citekey">naib-etal-2025-cuetraptors</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.125</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.125/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>739</start>
<end>745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T cuetRaptors@DravidianLangTech 2025: Transformer-Based Approaches for Detecting Abusive Tamil Text Targeting Women on Social Media
%A Naib, Md. Mubasshir
%A Shohag, Md. Saikat Hossain
%A Hossain, Alamgir
%A Hossain, Jawad
%A Hoque, Mohammed Moshiul
%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 naib-etal-2025-cuetraptors
%X With the exponential growth of social media usage, the prevalence of abusive language targeting women has become a pressing issue, particularly in low-resource languages (LRLs) like Tamil and Malayalam. This study is part of the shared task at DravidianLangTech@NAACL 2025, which focuses on detecting abusive comments in Tamil social media content. The provided dataset consists of binary-labeled comments (Abusive or Non-Abusive), gathered from YouTube, reflecting explicit abuse, implicit bias, stereotypes, and coded language. We developed and evaluated multiple models for this task, including traditional machine learning algorithms (Logistic Regression, Support Vector Machine, Random Forest Classifier, and Multinomial Naive Bayes), deep learning models (CNN, BiLSTM, and CNN+BiLSTM), and transformer-based architectures (DistilBERT, Multilingual BERT, XLM-RoBERTa), and fine-tuned variants of these models. Our best-performing model, Multilingual BERT, achieved a weighted F1-score of 0.7203, ranking 19 in the competition.
%R 10.18653/v1/2025.dravidianlangtech-1.125
%U https://aclanthology.org/2025.dravidianlangtech-1.125/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.125
%P 739-745
Markdown (Informal)
[cuetRaptors@DravidianLangTech 2025: Transformer-Based Approaches for Detecting Abusive Tamil Text Targeting Women on Social Media](https://aclanthology.org/2025.dravidianlangtech-1.125/) (Naib et al., DravidianLangTech 2025)
ACL
- Md. Mubasshir Naib, Md. Saikat Hossain Shohag, Alamgir Hossain, Jawad Hossain, and Mohammed Moshiul Hoque. 2025. cuetRaptors@DravidianLangTech 2025: Transformer-Based Approaches for Detecting Abusive Tamil Text Targeting Women on Social Media. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 739–745, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.