@inproceedings{shanmugavadivel-etal-2025-kec,
title = "{KEC}{\_}{AI}{\_}{DATA}{\_}{DRIFTERS}@{D}ravidian{L}ang{T}ech 2025: Fake News Detection in {D}ravidian Languages",
author = "Shanmugavadivel, Kogilavani and
Subramanian, Malliga and
S, Vishali K and
B, Priyanka and
K, Naveen Kumar",
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-1.29/",
doi = "10.18653/v1/2025.dravidianlangtech-1.29",
pages = "173--177",
ISBN = "979-8-89176-228-2",
abstract = "Detecting fake news in Malayalam possess significant challenges due to linguistic diversity, code-mixing, and the limited availability of structured datasets. We participated in the Fake News Detection in Dravidian Languages shared task, classifying news and social media posts into binary and multi-class categories. Our experiments used traditional ML models: Support Vector Machine (SVM), Random Forest, Logistic Regression, Naive Bayes and transfer learning models: Multilingual Bert (mBERT) and XLNet. In binary classification, SVM achieved the highest macro-F1 score of 0.97, while in multi-class classification, it also outperformed other models with a macro-F1 score of 0.98. Random Forest ranked second in both tasks. Despite their advanced capabilities, mBERT and XLNet exhibited lower precision due to data limitations. Our approach enhances fake news detection and NLP solutions for low-resource languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shanmugavadivel-etal-2025-kec">
<titleInfo>
<title>KEC_AI_DATA_DRIFTERS@DravidianLangTech 2025: Fake News Detection in Dravidian Languages</title>
</titleInfo>
<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">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishali</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">Priyanka</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naveen</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">K</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 fake news in Malayalam possess significant challenges due to linguistic diversity, code-mixing, and the limited availability of structured datasets. We participated in the Fake News Detection in Dravidian Languages shared task, classifying news and social media posts into binary and multi-class categories. Our experiments used traditional ML models: Support Vector Machine (SVM), Random Forest, Logistic Regression, Naive Bayes and transfer learning models: Multilingual Bert (mBERT) and XLNet. In binary classification, SVM achieved the highest macro-F1 score of 0.97, while in multi-class classification, it also outperformed other models with a macro-F1 score of 0.98. Random Forest ranked second in both tasks. Despite their advanced capabilities, mBERT and XLNet exhibited lower precision due to data limitations. Our approach enhances fake news detection and NLP solutions for low-resource languages.</abstract>
<identifier type="citekey">shanmugavadivel-etal-2025-kec</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.29</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.29/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>173</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KEC_AI_DATA_DRIFTERS@DravidianLangTech 2025: Fake News Detection in Dravidian Languages
%A Shanmugavadivel, Kogilavani
%A Subramanian, Malliga
%A S, Vishali K.
%A B, Priyanka
%A K, Naveen Kumar
%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 shanmugavadivel-etal-2025-kec
%X Detecting fake news in Malayalam possess significant challenges due to linguistic diversity, code-mixing, and the limited availability of structured datasets. We participated in the Fake News Detection in Dravidian Languages shared task, classifying news and social media posts into binary and multi-class categories. Our experiments used traditional ML models: Support Vector Machine (SVM), Random Forest, Logistic Regression, Naive Bayes and transfer learning models: Multilingual Bert (mBERT) and XLNet. In binary classification, SVM achieved the highest macro-F1 score of 0.97, while in multi-class classification, it also outperformed other models with a macro-F1 score of 0.98. Random Forest ranked second in both tasks. Despite their advanced capabilities, mBERT and XLNet exhibited lower precision due to data limitations. Our approach enhances fake news detection and NLP solutions for low-resource languages.
%R 10.18653/v1/2025.dravidianlangtech-1.29
%U https://aclanthology.org/2025.dravidianlangtech-1.29/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.29
%P 173-177
Markdown (Informal)
[KEC_AI_DATA_DRIFTERS@DravidianLangTech 2025: Fake News Detection in Dravidian Languages](https://aclanthology.org/2025.dravidianlangtech-1.29/) (Shanmugavadivel et al., DravidianLangTech 2025)
ACL
- Kogilavani Shanmugavadivel, Malliga Subramanian, Vishali K S, Priyanka B, and Naveen Kumar K. 2025. KEC_AI_DATA_DRIFTERS@DravidianLangTech 2025: Fake News Detection in Dravidian Languages. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 173–177, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.