@inproceedings{p-etal-2025-hermes,
title = "Hermes@{D}ravidian{L}ang{T}ech 2025: Sentiment Analysis of {D}ravidian Languages using {XLM}-{R}o{BERT}a",
author = "P, Emmanuel George and
Firoz, Ashiq and
Murali, Madhav and
Rajamanickam, Siranjeevi and
Palani, Balasubramanian",
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-1.58/",
doi = "10.18653/v1/2025.dravidianlangtech-1.58",
pages = "330--334",
ISBN = "979-8-89176-228-2",
abstract = "Sentiment analysis, the task of identifying subjective opinions or emotional responses, has become increasingly significant with the rise of social media. However, analysing sentiment in Dravidian languages such as Tamil-English and Tulu-English presents unique challenges due to linguistic code-switching (where people tend to mix multiple languages) and non-native scripts. Traditional monolingual sentiment analysis models struggle to address these complexities effectively. This research explores a fine-tuned transformer model based on the XLM-RoBERTa model for sentiment detection. It utilizes the tokenizer from the XLM-RoBERTa model for text preprocessing. Additionally, the performance of the XLM-RoBERTa model was compared with traditional machine learning models such as Logistic Regression (LR) and Random Forest (RF), as well as other transformer-based models like BERT and RoBERTa. This research was based on our work for the Sentiment Analysis in Tamil and Tulu DravidianLangTech@NAACL 2025 competition, where we received a macro F1-score of 59{\%} for the Tulu dataset and 49{\%} for the Tamil dataset, placing third in the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="p-etal-2025-hermes">
<titleInfo>
<title>Hermes@DravidianLangTech 2025: Sentiment Analysis of Dravidian Languages using XLM-RoBERTa</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="given">George</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashiq</namePart>
<namePart type="family">Firoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhav</namePart>
<namePart type="family">Murali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siranjeevi</namePart>
<namePart type="family">Rajamanickam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</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, the task of identifying subjective opinions or emotional responses, has become increasingly significant with the rise of social media. However, analysing sentiment in Dravidian languages such as Tamil-English and Tulu-English presents unique challenges due to linguistic code-switching (where people tend to mix multiple languages) and non-native scripts. Traditional monolingual sentiment analysis models struggle to address these complexities effectively. This research explores a fine-tuned transformer model based on the XLM-RoBERTa model for sentiment detection. It utilizes the tokenizer from the XLM-RoBERTa model for text preprocessing. Additionally, the performance of the XLM-RoBERTa model was compared with traditional machine learning models such as Logistic Regression (LR) and Random Forest (RF), as well as other transformer-based models like BERT and RoBERTa. This research was based on our work for the Sentiment Analysis in Tamil and Tulu DravidianLangTech@NAACL 2025 competition, where we received a macro F1-score of 59% for the Tulu dataset and 49% for the Tamil dataset, placing third in the competition.</abstract>
<identifier type="citekey">p-etal-2025-hermes</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.58</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.58/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>330</start>
<end>334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hermes@DravidianLangTech 2025: Sentiment Analysis of Dravidian Languages using XLM-RoBERTa
%A P, Emmanuel George
%A Firoz, Ashiq
%A Murali, Madhav
%A Rajamanickam, Siranjeevi
%A Palani, Balasubramanian
%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 p-etal-2025-hermes
%X Sentiment analysis, the task of identifying subjective opinions or emotional responses, has become increasingly significant with the rise of social media. However, analysing sentiment in Dravidian languages such as Tamil-English and Tulu-English presents unique challenges due to linguistic code-switching (where people tend to mix multiple languages) and non-native scripts. Traditional monolingual sentiment analysis models struggle to address these complexities effectively. This research explores a fine-tuned transformer model based on the XLM-RoBERTa model for sentiment detection. It utilizes the tokenizer from the XLM-RoBERTa model for text preprocessing. Additionally, the performance of the XLM-RoBERTa model was compared with traditional machine learning models such as Logistic Regression (LR) and Random Forest (RF), as well as other transformer-based models like BERT and RoBERTa. This research was based on our work for the Sentiment Analysis in Tamil and Tulu DravidianLangTech@NAACL 2025 competition, where we received a macro F1-score of 59% for the Tulu dataset and 49% for the Tamil dataset, placing third in the competition.
%R 10.18653/v1/2025.dravidianlangtech-1.58
%U https://aclanthology.org/2025.dravidianlangtech-1.58/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.58
%P 330-334
Markdown (Informal)
[Hermes@DravidianLangTech 2025: Sentiment Analysis of Dravidian Languages using XLM-RoBERTa](https://aclanthology.org/2025.dravidianlangtech-1.58/) (P et al., DravidianLangTech 2025)
ACL
- Emmanuel George P, Ashiq Firoz, Madhav Murali, Siranjeevi Rajamanickam, and Balasubramanian Palani. 2025. Hermes@DravidianLangTech 2025: Sentiment Analysis of Dravidian Languages using XLM-RoBERTa. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 330–334, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.