@inproceedings{thevakumar-thevakumar-2025-rathan,
title = "{RATHAN}@{D}ravidian{L}ang{T}ech 2025: Annaparavai - Separate the Authentic Human Reviews from {AI}-generated one",
author = "Thevakumar, Jubeerathan and
Thevakumar, Luheerathan",
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-1.66/",
doi = "10.18653/v1/2025.dravidianlangtech-1.66",
pages = "371--375",
ISBN = "979-8-89176-228-2",
abstract = "Detecting AI-generated reviews is crucial for maintaining the authenticity of online feedback in low-resource languages like Tamil and Malayalam. We propose a transfer learning-based approach using embeddings from XLM-RoBERTa, IndicBERT, mT5, and Sentence-BERT, validated with five-fold cross-validation via XGBoost. These embeddings are used to train deep neural networks (DNNs), refined through a weighted ensemble model. Our method achieves 90{\%} F1-score for Malayalam and 73{\%} for Tamil, demonstrating the effectiveness of transfer learning and ensembling for review detection. The source code is publicly available to support further research and improve online review systems in multilingual settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thevakumar-thevakumar-2025-rathan">
<titleInfo>
<title>RATHAN@DravidianLangTech 2025: Annaparavai - Separate the Authentic Human Reviews from AI-generated one</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jubeerathan</namePart>
<namePart type="family">Thevakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luheerathan</namePart>
<namePart type="family">Thevakumar</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>Detecting AI-generated reviews is crucial for maintaining the authenticity of online feedback in low-resource languages like Tamil and Malayalam. We propose a transfer learning-based approach using embeddings from XLM-RoBERTa, IndicBERT, mT5, and Sentence-BERT, validated with five-fold cross-validation via XGBoost. These embeddings are used to train deep neural networks (DNNs), refined through a weighted ensemble model. Our method achieves 90% F1-score for Malayalam and 73% for Tamil, demonstrating the effectiveness of transfer learning and ensembling for review detection. The source code is publicly available to support further research and improve online review systems in multilingual settings.</abstract>
<identifier type="citekey">thevakumar-thevakumar-2025-rathan</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.66</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.66/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>371</start>
<end>375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RATHAN@DravidianLangTech 2025: Annaparavai - Separate the Authentic Human Reviews from AI-generated one
%A Thevakumar, Jubeerathan
%A Thevakumar, Luheerathan
%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 thevakumar-thevakumar-2025-rathan
%X Detecting AI-generated reviews is crucial for maintaining the authenticity of online feedback in low-resource languages like Tamil and Malayalam. We propose a transfer learning-based approach using embeddings from XLM-RoBERTa, IndicBERT, mT5, and Sentence-BERT, validated with five-fold cross-validation via XGBoost. These embeddings are used to train deep neural networks (DNNs), refined through a weighted ensemble model. Our method achieves 90% F1-score for Malayalam and 73% for Tamil, demonstrating the effectiveness of transfer learning and ensembling for review detection. The source code is publicly available to support further research and improve online review systems in multilingual settings.
%R 10.18653/v1/2025.dravidianlangtech-1.66
%U https://aclanthology.org/2025.dravidianlangtech-1.66/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.66
%P 371-375
Markdown (Informal)
[RATHAN@DravidianLangTech 2025: Annaparavai - Separate the Authentic Human Reviews from AI-generated one](https://aclanthology.org/2025.dravidianlangtech-1.66/) (Thevakumar & Thevakumar, DravidianLangTech 2025)
ACL