@inproceedings{subramanian-etal-2025-kecempower,
title = "{KECE}mpower@{D}ravidian{L}ang{T}ech 2025: Abusive {T}amil and {M}alayalam Text targeting Women on Social Media",
author = "Subramanian, Malliga and
Shanmugavadivel, Kogilavani and
S, Indhuja V and
P, Kowshik and
S, Jayasurya",
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-1.30/",
doi = "10.18653/v1/2025.dravidianlangtech-1.30",
pages = "178--181",
ISBN = "979-8-89176-228-2",
abstract = "The detection of abusive text targeting women, especially in Dravidian languages like Tamil and Malayalam, presents a unique challenge due to linguistic complexities and code-mixing on social media. This paper evaluates machine learning models such as Support Vector Machines (SVM), Logistic Regression (LR), and Random Forest Classifiers (RFC) for identifying abusive content. Code-mixed datasets sourced from platforms like YouTube are used to train and test the models. Performance is evaluated using accuracy, precision, recall, and F1-score metrics. Our findings show that SVM outperforms the other classifiers in accuracy and recall. However, challenges persist in detecting implicit abuse and addressing informal, culturally nuanced language. Future work will explore transformer-based models like BERT for better context understanding, along with data augmentation techniques to enhance model performance. Additionally, efforts will focus on expanding labeled datasets to improve abuse detection in these low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="subramanian-etal-2025-kecempower">
<titleInfo>
<title>KECEmpower@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media</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">Indhuja</namePart>
<namePart type="given">V</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kowshik</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayasurya</namePart>
<namePart type="family">S</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>The detection of abusive text targeting women, especially in Dravidian languages like Tamil and Malayalam, presents a unique challenge due to linguistic complexities and code-mixing on social media. This paper evaluates machine learning models such as Support Vector Machines (SVM), Logistic Regression (LR), and Random Forest Classifiers (RFC) for identifying abusive content. Code-mixed datasets sourced from platforms like YouTube are used to train and test the models. Performance is evaluated using accuracy, precision, recall, and F1-score metrics. Our findings show that SVM outperforms the other classifiers in accuracy and recall. However, challenges persist in detecting implicit abuse and addressing informal, culturally nuanced language. Future work will explore transformer-based models like BERT for better context understanding, along with data augmentation techniques to enhance model performance. Additionally, efforts will focus on expanding labeled datasets to improve abuse detection in these low-resource languages.</abstract>
<identifier type="citekey">subramanian-etal-2025-kecempower</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.30</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.30/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>178</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KECEmpower@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media
%A Subramanian, Malliga
%A Shanmugavadivel, Kogilavani
%A S, Indhuja V.
%A P, Kowshik
%A S, Jayasurya
%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-kecempower
%X The detection of abusive text targeting women, especially in Dravidian languages like Tamil and Malayalam, presents a unique challenge due to linguistic complexities and code-mixing on social media. This paper evaluates machine learning models such as Support Vector Machines (SVM), Logistic Regression (LR), and Random Forest Classifiers (RFC) for identifying abusive content. Code-mixed datasets sourced from platforms like YouTube are used to train and test the models. Performance is evaluated using accuracy, precision, recall, and F1-score metrics. Our findings show that SVM outperforms the other classifiers in accuracy and recall. However, challenges persist in detecting implicit abuse and addressing informal, culturally nuanced language. Future work will explore transformer-based models like BERT for better context understanding, along with data augmentation techniques to enhance model performance. Additionally, efforts will focus on expanding labeled datasets to improve abuse detection in these low-resource languages.
%R 10.18653/v1/2025.dravidianlangtech-1.30
%U https://aclanthology.org/2025.dravidianlangtech-1.30/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.30
%P 178-181
Markdown (Informal)
[KECEmpower@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media](https://aclanthology.org/2025.dravidianlangtech-1.30/) (Subramanian et al., DravidianLangTech 2025)
ACL
- Malliga Subramanian, Kogilavani Shanmugavadivel, Indhuja V S, Kowshik P, and Jayasurya S. 2025. KECEmpower@DravidianLangTech 2025: Abusive Tamil and Malayalam Text targeting Women on Social Media. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 178–181, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.