@inproceedings{chowdhury-etal-2025-mysticciol,
title = "{M}ystic{CIOL}@{D}ravidian{L}ang{T}ech 2025: A Hybrid Framework for Sentiment Analysis in {T}amil and {T}ulu Using Fine-Tuned {SBERT} Embeddings and Custom {MLP} Architectures",
author = "Chowdhury, Minhaz and
Laskar, Arnab and
Ahmad, Taj and
Wasi, Azmine Toushik",
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-1.28/",
doi = "10.18653/v1/2025.dravidianlangtech-1.28",
pages = "167--172",
ISBN = "979-8-89176-228-2",
abstract = "Sentiment analysis is a crucial NLP task used to analyze opinions in various domains, including marketing, politics, and social media. While transformer-based models like BERT and SBERT have significantly improved sentiment classification, their effectiveness in low-resource languages remains limited. Tamil and Tulu, despite their widespread use, suffer from data scarcity, dialectal variations, and code-mixing challenges, making sentiment analysis difficult. Existing methods rely on traditional classifiers or word embeddings, which struggle to generalize in these settings. To address this, we propose a hybrid framework that integrates fine-tuned SBERT embeddings with a Multi-Layer Perceptron (MLP) classifier, enhancing contextual representation and classification robustness. Our framework achieves validation F1-scores of 0.4218 for Tamil and 0.3935 for Tulu and test F1-scores of 0.4299 in Tamil and 0.1546 on Tulu, demonstrating its effectiveness. This research provides a scalable solution for sentiment classification in low-resource languages, with future improvements planned through data augmentation and transfer learning. Our full experimental codebase is publicly available at: github.com/ciol-researchlab/NAACL25-Mystic-Tamil-Sentiment-Analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2025-mysticciol">
<titleInfo>
<title>MysticCIOL@DravidianLangTech 2025: A Hybrid Framework for Sentiment Analysis in Tamil and Tulu Using Fine-Tuned SBERT Embeddings and Custom MLP Architectures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minhaz</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taj</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azmine</namePart>
<namePart type="given">Toushik</namePart>
<namePart type="family">Wasi</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>Sentiment analysis is a crucial NLP task used to analyze opinions in various domains, including marketing, politics, and social media. While transformer-based models like BERT and SBERT have significantly improved sentiment classification, their effectiveness in low-resource languages remains limited. Tamil and Tulu, despite their widespread use, suffer from data scarcity, dialectal variations, and code-mixing challenges, making sentiment analysis difficult. Existing methods rely on traditional classifiers or word embeddings, which struggle to generalize in these settings. To address this, we propose a hybrid framework that integrates fine-tuned SBERT embeddings with a Multi-Layer Perceptron (MLP) classifier, enhancing contextual representation and classification robustness. Our framework achieves validation F1-scores of 0.4218 for Tamil and 0.3935 for Tulu and test F1-scores of 0.4299 in Tamil and 0.1546 on Tulu, demonstrating its effectiveness. This research provides a scalable solution for sentiment classification in low-resource languages, with future improvements planned through data augmentation and transfer learning. Our full experimental codebase is publicly available at: github.com/ciol-researchlab/NAACL25-Mystic-Tamil-Sentiment-Analysis.</abstract>
<identifier type="citekey">chowdhury-etal-2025-mysticciol</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.28</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.28/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>167</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MysticCIOL@DravidianLangTech 2025: A Hybrid Framework for Sentiment Analysis in Tamil and Tulu Using Fine-Tuned SBERT Embeddings and Custom MLP Architectures
%A Chowdhury, Minhaz
%A Laskar, Arnab
%A Ahmad, Taj
%A Wasi, Azmine Toushik
%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 chowdhury-etal-2025-mysticciol
%X Sentiment analysis is a crucial NLP task used to analyze opinions in various domains, including marketing, politics, and social media. While transformer-based models like BERT and SBERT have significantly improved sentiment classification, their effectiveness in low-resource languages remains limited. Tamil and Tulu, despite their widespread use, suffer from data scarcity, dialectal variations, and code-mixing challenges, making sentiment analysis difficult. Existing methods rely on traditional classifiers or word embeddings, which struggle to generalize in these settings. To address this, we propose a hybrid framework that integrates fine-tuned SBERT embeddings with a Multi-Layer Perceptron (MLP) classifier, enhancing contextual representation and classification robustness. Our framework achieves validation F1-scores of 0.4218 for Tamil and 0.3935 for Tulu and test F1-scores of 0.4299 in Tamil and 0.1546 on Tulu, demonstrating its effectiveness. This research provides a scalable solution for sentiment classification in low-resource languages, with future improvements planned through data augmentation and transfer learning. Our full experimental codebase is publicly available at: github.com/ciol-researchlab/NAACL25-Mystic-Tamil-Sentiment-Analysis.
%R 10.18653/v1/2025.dravidianlangtech-1.28
%U https://aclanthology.org/2025.dravidianlangtech-1.28/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.28
%P 167-172
Markdown (Informal)
[MysticCIOL@DravidianLangTech 2025: A Hybrid Framework for Sentiment Analysis in Tamil and Tulu Using Fine-Tuned SBERT Embeddings and Custom MLP Architectures](https://aclanthology.org/2025.dravidianlangtech-1.28/) (Chowdhury et al., DravidianLangTech 2025)
ACL
- Minhaz Chowdhury, Arnab Laskar, Taj Ahmad, and Azmine Toushik Wasi. 2025. MysticCIOL@DravidianLangTech 2025: A Hybrid Framework for Sentiment Analysis in Tamil and Tulu Using Fine-Tuned SBERT Embeddings and Custom MLP Architectures. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 167–172, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.