@inproceedings{s-etal-2026-lannisters,
title = "Lannisters@{D}ravidian{L}ang{T}ech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in {T}amil Social Media Platforms",
author = "S, Kalaivani K and
K, Jaisanth and
B, Nandhini",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Rajiakodi, Saranya and
Navaneethakrishnan, Subalalitha and
Chinnappa, Dhivya and
Palani, Balasubramanian and
Subramanian, Malliga and
Shanmugavadivel, Kogilavani and
Rajalakshmi, Ratnavel",
booktitle = "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for {D}ravidian Languages",
month = jul,
year = "2026",
address = "Underline (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dravidianlangtech-1.44/",
pages = "289--293",
ISBN = "979-8-89176-401-9",
abstract = "The prevalence of the use of the Tamil lan- guage on social media has heightened the need to address the issue of online harassment of women. As a result, there is a heightened need to develop a system to automatically iden- tify abusive content in the Tamil language to promote a safe online communication plat- form. This paper presents a model to iden- tify abusive content using a binary classifi- cation model to identify Abusive and Non- Abusive content. In this work, we experi- mented with several multilingual transformer models including DistilBERT, mBERT, and XLM-RoBERTa. From the experiments, it was observed that the XLM-RoBERTa model performed better than the others, achieving an accuracy of 91.17{\%} and a macro F1 score of 0.8865. In this paper, ablation experiments are conducted to show that structured preprocess- ing, balancing the minority class, and tuning the hyperparameters contribute to the model{'}s performance"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-etal-2026-lannisters">
<titleInfo>
<title>Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalaivani</namePart>
<namePart type="given">K</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaisanth</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nandhini</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Navaneethakrishnan</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>
<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">Kogilavani</namePart>
<namePart type="family">Shanmugavadivel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnavel</namePart>
<namePart type="family">Rajalakshmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Underline (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-401-9</identifier>
</relatedItem>
<abstract>The prevalence of the use of the Tamil lan- guage on social media has heightened the need to address the issue of online harassment of women. As a result, there is a heightened need to develop a system to automatically iden- tify abusive content in the Tamil language to promote a safe online communication plat- form. This paper presents a model to iden- tify abusive content using a binary classifi- cation model to identify Abusive and Non- Abusive content. In this work, we experi- mented with several multilingual transformer models including DistilBERT, mBERT, and XLM-RoBERTa. From the experiments, it was observed that the XLM-RoBERTa model performed better than the others, achieving an accuracy of 91.17% and a macro F1 score of 0.8865. In this paper, ablation experiments are conducted to show that structured preprocess- ing, balancing the minority class, and tuning the hyperparameters contribute to the model’s performance</abstract>
<identifier type="citekey">s-etal-2026-lannisters</identifier>
<location>
<url>https://aclanthology.org/2026.dravidianlangtech-1.44/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>289</start>
<end>293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms
%A S, Kalaivani K.
%A K, Jaisanth
%A B, Nandhini
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Rajiakodi, Saranya
%Y Navaneethakrishnan, Subalalitha
%Y Chinnappa, Dhivya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Shanmugavadivel, Kogilavani
%Y Rajalakshmi, Ratnavel
%S Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2026
%8 July
%I Association for Computational Linguistics
%C Underline (Virtual)
%@ 979-8-89176-401-9
%F s-etal-2026-lannisters
%X The prevalence of the use of the Tamil lan- guage on social media has heightened the need to address the issue of online harassment of women. As a result, there is a heightened need to develop a system to automatically iden- tify abusive content in the Tamil language to promote a safe online communication plat- form. This paper presents a model to iden- tify abusive content using a binary classifi- cation model to identify Abusive and Non- Abusive content. In this work, we experi- mented with several multilingual transformer models including DistilBERT, mBERT, and XLM-RoBERTa. From the experiments, it was observed that the XLM-RoBERTa model performed better than the others, achieving an accuracy of 91.17% and a macro F1 score of 0.8865. In this paper, ablation experiments are conducted to show that structured preprocess- ing, balancing the minority class, and tuning the hyperparameters contribute to the model’s performance
%U https://aclanthology.org/2026.dravidianlangtech-1.44/
%P 289-293
Markdown (Informal)
[Lannisters@DravidianLangTech 2026: A Comparative and Ablation Study of Multilingual Transformers for Gender-Targeted Abuse Detection in Tamil Social Media Platforms](https://aclanthology.org/2026.dravidianlangtech-1.44/) (S et al., DravidianLangTech 2026)
ACL