@inproceedings{chakraborty-etal-2025-one-zero,
title = "One{\_}by{\_}zero@{D}ravidian{L}ang{T}ech 2025: Fake News Detection in {M}alayalam Language Leveraging Transformer-based Approach",
author = "Chakraborty, Dola and
Afroz, Shamima and
Hossain, Jawad and
Hoque, Mohammed Moshiul",
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-1.82/",
doi = "10.18653/v1/2025.dravidianlangtech-1.82",
pages = "465--471",
ISBN = "979-8-89176-228-2",
abstract = "The rapid spread of misinformation in the digital era presents critical challenges for fake news detection, especially in low-resource languages (LRLs) like Malayalam, which lack extensive datasets and pre-trained models for widely spoken languages. This gap in resources makes it harder to build robust systems for combating misinformation despite the significant societal and political consequences it can have. To address these challenges, this work proposes a transformer-based approach for Task 1 of the Fake News Detection in Dravidian Languages (DravidianLangTech@NAACL 2025), which focuses on classifying Malayalam social media texts as either \textit{original} or \textit{fake}. The experiments involved a range of ML techniques (Logistic Regression (LR), Support Vector Machines (SVM), and Decision Trees (DT)) and DL architectures (BiLSTM, BiLSTM-LSTM, and BiLSTM-CNN). This work also explored transformer-based models, including IndicBERT, MuRiL, XLM-RoBERTa, and Malayalam BERT. Among these, Malayalam BERT achieved the best performance, with the highest macro F1-score of 0.892, securing a rank of 3rd in the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2025-one-zero">
<titleInfo>
<title>One_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dola</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamima</namePart>
<namePart type="family">Afroz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jawad</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</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 rapid spread of misinformation in the digital era presents critical challenges for fake news detection, especially in low-resource languages (LRLs) like Malayalam, which lack extensive datasets and pre-trained models for widely spoken languages. This gap in resources makes it harder to build robust systems for combating misinformation despite the significant societal and political consequences it can have. To address these challenges, this work proposes a transformer-based approach for Task 1 of the Fake News Detection in Dravidian Languages (DravidianLangTech@NAACL 2025), which focuses on classifying Malayalam social media texts as either original or fake. The experiments involved a range of ML techniques (Logistic Regression (LR), Support Vector Machines (SVM), and Decision Trees (DT)) and DL architectures (BiLSTM, BiLSTM-LSTM, and BiLSTM-CNN). This work also explored transformer-based models, including IndicBERT, MuRiL, XLM-RoBERTa, and Malayalam BERT. Among these, Malayalam BERT achieved the best performance, with the highest macro F1-score of 0.892, securing a rank of 3rd in the competition.</abstract>
<identifier type="citekey">chakraborty-etal-2025-one-zero</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.82</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.82/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>465</start>
<end>471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based Approach
%A Chakraborty, Dola
%A Afroz, Shamima
%A Hossain, Jawad
%A Hoque, Mohammed Moshiul
%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 chakraborty-etal-2025-one-zero
%X The rapid spread of misinformation in the digital era presents critical challenges for fake news detection, especially in low-resource languages (LRLs) like Malayalam, which lack extensive datasets and pre-trained models for widely spoken languages. This gap in resources makes it harder to build robust systems for combating misinformation despite the significant societal and political consequences it can have. To address these challenges, this work proposes a transformer-based approach for Task 1 of the Fake News Detection in Dravidian Languages (DravidianLangTech@NAACL 2025), which focuses on classifying Malayalam social media texts as either original or fake. The experiments involved a range of ML techniques (Logistic Regression (LR), Support Vector Machines (SVM), and Decision Trees (DT)) and DL architectures (BiLSTM, BiLSTM-LSTM, and BiLSTM-CNN). This work also explored transformer-based models, including IndicBERT, MuRiL, XLM-RoBERTa, and Malayalam BERT. Among these, Malayalam BERT achieved the best performance, with the highest macro F1-score of 0.892, securing a rank of 3rd in the competition.
%R 10.18653/v1/2025.dravidianlangtech-1.82
%U https://aclanthology.org/2025.dravidianlangtech-1.82/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.82
%P 465-471
Markdown (Informal)
[One_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based Approach](https://aclanthology.org/2025.dravidianlangtech-1.82/) (Chakraborty et al., DravidianLangTech 2025)
ACL
- Dola Chakraborty, Shamima Afroz, Jawad Hossain, and Mohammed Moshiul Hoque. 2025. One_by_zero@DravidianLangTech 2025: Fake News Detection in Malayalam Language Leveraging Transformer-based Approach. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 465–471, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.