@inproceedings{rebayet-etal-2026-trivector,
title = "{T}ri{V}ector@{D}ravidian{L}ang{T}ech 2026: Abusive {T}amil Text Detection on Social Media Using Lexicon-Augmented Transformers",
author = "Rebayet, Oarisa and
Eid, Tahmima Hoque and
Tabassum, Fawzia and
Murad, Hasan",
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-1.67/",
pages = "420--428",
ISBN = "979-8-89176-401-9",
abstract = "Abusive comment detection in low-resource languages poses significant challenges, particularly when targeting gender-based abuse on social media platforms. This work presents our system for `Abusive Tamil text targeting women on social media' at DravidianLangTech@ACL 2026. We introduce nine handcrafted lexicon features integrated with pretrained multilingual transformer embeddings and evaluate their effectiveness in classifying Tamil online comments as abusive or non-abusive. To better understand their impact, we compare model performance with and without these lexical attributes across multiple transformer architectures. Our best-performing model, XLM-RoBERTa-Large, achieved a macro F1-score of 81.71{\%}, securing 15th rank in the competition. The findings indicate that larger multilingual models generalize more effectively to unseen data compared to smaller domain-specific models, while the addition of lexical features yields only mild gains."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rebayet-etal-2026-trivector">
<titleInfo>
<title>TriVector@DravidianLangTech 2026: Abusive Tamil Text Detection on Social Media Using Lexicon-Augmented Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oarisa</namePart>
<namePart type="family">Rebayet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tahmima</namePart>
<namePart type="given">Hoque</namePart>
<namePart type="family">Eid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fawzia</namePart>
<namePart type="family">Tabassum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</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>Abusive comment detection in low-resource languages poses significant challenges, particularly when targeting gender-based abuse on social media platforms. This work presents our system for ‘Abusive Tamil text targeting women on social media’ at DravidianLangTech@ACL 2026. We introduce nine handcrafted lexicon features integrated with pretrained multilingual transformer embeddings and evaluate their effectiveness in classifying Tamil online comments as abusive or non-abusive. To better understand their impact, we compare model performance with and without these lexical attributes across multiple transformer architectures. Our best-performing model, XLM-RoBERTa-Large, achieved a macro F1-score of 81.71%, securing 15th rank in the competition. The findings indicate that larger multilingual models generalize more effectively to unseen data compared to smaller domain-specific models, while the addition of lexical features yields only mild gains.</abstract>
<identifier type="citekey">rebayet-etal-2026-trivector</identifier>
<location>
<url>https://aclanthology.org/2026.dravidianlangtech-1.67/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>420</start>
<end>428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TriVector@DravidianLangTech 2026: Abusive Tamil Text Detection on Social Media Using Lexicon-Augmented Transformers
%A Rebayet, Oarisa
%A Eid, Tahmima Hoque
%A Tabassum, Fawzia
%A Murad, Hasan
%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 rebayet-etal-2026-trivector
%X Abusive comment detection in low-resource languages poses significant challenges, particularly when targeting gender-based abuse on social media platforms. This work presents our system for ‘Abusive Tamil text targeting women on social media’ at DravidianLangTech@ACL 2026. We introduce nine handcrafted lexicon features integrated with pretrained multilingual transformer embeddings and evaluate their effectiveness in classifying Tamil online comments as abusive or non-abusive. To better understand their impact, we compare model performance with and without these lexical attributes across multiple transformer architectures. Our best-performing model, XLM-RoBERTa-Large, achieved a macro F1-score of 81.71%, securing 15th rank in the competition. The findings indicate that larger multilingual models generalize more effectively to unseen data compared to smaller domain-specific models, while the addition of lexical features yields only mild gains.
%U https://aclanthology.org/2026.dravidianlangtech-1.67/
%P 420-428
Markdown (Informal)
[TriVector@DravidianLangTech 2026: Abusive Tamil Text Detection on Social Media Using Lexicon-Augmented Transformers](https://aclanthology.org/2026.dravidianlangtech-1.67/) (Rebayet et al., DravidianLangTech 2026)
ACL