@inproceedings{bhuvana-etal-2025-ssntrio,
title = "{SSNT}rio@{D}ravidian{L}ang{T}ech 2025: Identification of {AI} Generated Content in {D}ravidian Languages using Transformers",
author = "Bhuvana, J and
T T, Mirnalinee and
R, Rohan and
Seshan, Diya and
Koushik, Avaneesh",
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-1.59/",
doi = "10.18653/v1/2025.dravidianlangtech-1.59",
pages = "335--339",
ISBN = "979-8-89176-228-2",
abstract = "The increasing prevalence of AI-generated content has raised concerns about the authenticity and reliability of online reviews, particularly in resource-limited languages like Tamil and Malayalam. This paper presents an approach to the Shared Task on Detecting AI-generated Product Reviews in Dravidian Languages at NAACL2025, which focuses on distinguishing AI-generated reviews from human-written ones in Tamil and Malayalam. Several transformer-based models, including IndicBERT, RoBERTa, mBERT, and XLM-R, were evaluated, with language-specific BERT models for Tamil and Malayalam demonstrating the best performance. The chosen methodologies were evaluated using Macro Average F1 score. In the rank list released by the organizers, team SSNTrio, achieved ranks of 3rd and 29th for the Malayalam and Tamil datasets with Macro Average F1 Scores of 0.914 and 0.598 respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhuvana-etal-2025-ssntrio">
<titleInfo>
<title>SSNTrio@DravidianLangTech 2025: Identification of AI Generated Content in Dravidian Languages using Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="family">Bhuvana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirnalinee</namePart>
<namePart type="family">T T</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohan</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diya</namePart>
<namePart type="family">Seshan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avaneesh</namePart>
<namePart type="family">Koushik</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 increasing prevalence of AI-generated content has raised concerns about the authenticity and reliability of online reviews, particularly in resource-limited languages like Tamil and Malayalam. This paper presents an approach to the Shared Task on Detecting AI-generated Product Reviews in Dravidian Languages at NAACL2025, which focuses on distinguishing AI-generated reviews from human-written ones in Tamil and Malayalam. Several transformer-based models, including IndicBERT, RoBERTa, mBERT, and XLM-R, were evaluated, with language-specific BERT models for Tamil and Malayalam demonstrating the best performance. The chosen methodologies were evaluated using Macro Average F1 score. In the rank list released by the organizers, team SSNTrio, achieved ranks of 3rd and 29th for the Malayalam and Tamil datasets with Macro Average F1 Scores of 0.914 and 0.598 respectively.</abstract>
<identifier type="citekey">bhuvana-etal-2025-ssntrio</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.59</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.59/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>335</start>
<end>339</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSNTrio@DravidianLangTech 2025: Identification of AI Generated Content in Dravidian Languages using Transformers
%A Bhuvana, J.
%A T T, Mirnalinee
%A R, Rohan
%A Seshan, Diya
%A Koushik, Avaneesh
%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 bhuvana-etal-2025-ssntrio
%X The increasing prevalence of AI-generated content has raised concerns about the authenticity and reliability of online reviews, particularly in resource-limited languages like Tamil and Malayalam. This paper presents an approach to the Shared Task on Detecting AI-generated Product Reviews in Dravidian Languages at NAACL2025, which focuses on distinguishing AI-generated reviews from human-written ones in Tamil and Malayalam. Several transformer-based models, including IndicBERT, RoBERTa, mBERT, and XLM-R, were evaluated, with language-specific BERT models for Tamil and Malayalam demonstrating the best performance. The chosen methodologies were evaluated using Macro Average F1 score. In the rank list released by the organizers, team SSNTrio, achieved ranks of 3rd and 29th for the Malayalam and Tamil datasets with Macro Average F1 Scores of 0.914 and 0.598 respectively.
%R 10.18653/v1/2025.dravidianlangtech-1.59
%U https://aclanthology.org/2025.dravidianlangtech-1.59/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.59
%P 335-339
Markdown (Informal)
[SSNTrio@DravidianLangTech 2025: Identification of AI Generated Content in Dravidian Languages using Transformers](https://aclanthology.org/2025.dravidianlangtech-1.59/) (Bhuvana et al., DravidianLangTech 2025)
ACL
- J Bhuvana, Mirnalinee T T, Rohan R, Diya Seshan, and Avaneesh Koushik. 2025. SSNTrio@DravidianLangTech 2025: Identification of AI Generated Content in Dravidian Languages using Transformers. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 335–339, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.