@inproceedings{balachandran-etal-2025-towards,
title = "Towards Effective Emotion Analysis in Low-Resource {T}amil Texts",
author = "Balachandran, Priyatharshan and
Thayasivam, Uthayasanker and
Pushpananda, Randil and
Weerasinghe, Ruvan",
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-1.101/",
doi = "10.18653/v1/2025.dravidianlangtech-1.101",
pages = "585--598",
ISBN = "979-8-89176-228-2",
abstract = "Emotion analysis plays a significant role in understanding human behavior and communication, yet research in Tamil language remains limited. This study focuses on building an emotion classifier for Tamil texts using machine learning (ML) and deep learning (DL), along with creating an emotion-annotated Tamil corpus for Ekman{'}s basic emotions. Our dataset combines publicly available data with re-annotation and translations. Along with traditional ML models we investigated the use of Transfer Learning (TL) with state-of-the-art models, such as BERT and Electra based models. Experiments were conducted on unbalanced and balanced datasets using data augmentation techniques. The results indicate that MultinomialNaive Bayes (MNB) and Support Vector Machine (SVM) performed well with TF-IDF and BoW representations, while among Transfer Learning models, LaBSE achieved the highest accuracy (63{\%} balanced, 69{\%} unbalanced), followed by TamilBERT and IndicBERT."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balachandran-etal-2025-towards">
<titleInfo>
<title>Towards Effective Emotion Analysis in Low-Resource Tamil Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priyatharshan</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uthayasanker</namePart>
<namePart type="family">Thayasivam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Randil</namePart>
<namePart type="family">Pushpananda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruvan</namePart>
<namePart type="family">Weerasinghe</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>Emotion analysis plays a significant role in understanding human behavior and communication, yet research in Tamil language remains limited. This study focuses on building an emotion classifier for Tamil texts using machine learning (ML) and deep learning (DL), along with creating an emotion-annotated Tamil corpus for Ekman’s basic emotions. Our dataset combines publicly available data with re-annotation and translations. Along with traditional ML models we investigated the use of Transfer Learning (TL) with state-of-the-art models, such as BERT and Electra based models. Experiments were conducted on unbalanced and balanced datasets using data augmentation techniques. The results indicate that MultinomialNaive Bayes (MNB) and Support Vector Machine (SVM) performed well with TF-IDF and BoW representations, while among Transfer Learning models, LaBSE achieved the highest accuracy (63% balanced, 69% unbalanced), followed by TamilBERT and IndicBERT.</abstract>
<identifier type="citekey">balachandran-etal-2025-towards</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.101</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.101/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>585</start>
<end>598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Effective Emotion Analysis in Low-Resource Tamil Texts
%A Balachandran, Priyatharshan
%A Thayasivam, Uthayasanker
%A Pushpananda, Randil
%A Weerasinghe, Ruvan
%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 balachandran-etal-2025-towards
%X Emotion analysis plays a significant role in understanding human behavior and communication, yet research in Tamil language remains limited. This study focuses on building an emotion classifier for Tamil texts using machine learning (ML) and deep learning (DL), along with creating an emotion-annotated Tamil corpus for Ekman’s basic emotions. Our dataset combines publicly available data with re-annotation and translations. Along with traditional ML models we investigated the use of Transfer Learning (TL) with state-of-the-art models, such as BERT and Electra based models. Experiments were conducted on unbalanced and balanced datasets using data augmentation techniques. The results indicate that MultinomialNaive Bayes (MNB) and Support Vector Machine (SVM) performed well with TF-IDF and BoW representations, while among Transfer Learning models, LaBSE achieved the highest accuracy (63% balanced, 69% unbalanced), followed by TamilBERT and IndicBERT.
%R 10.18653/v1/2025.dravidianlangtech-1.101
%U https://aclanthology.org/2025.dravidianlangtech-1.101/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.101
%P 585-598
Markdown (Informal)
[Towards Effective Emotion Analysis in Low-Resource Tamil Texts](https://aclanthology.org/2025.dravidianlangtech-1.101/) (Balachandran et al., DravidianLangTech 2025)
ACL
- Priyatharshan Balachandran, Uthayasanker Thayasivam, Randil Pushpananda, and Ruvan Weerasinghe. 2025. Towards Effective Emotion Analysis in Low-Resource Tamil Texts. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 585–598, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.