@inproceedings{adyanthaya-p-2025-yenlp,
title = "{Y}en{LP}{\_}{CS}@{D}ravidian{L}ang{T}ech 2025: Sentiment Analysis on Code-Mixed {T}amil-{T}ulu Data Using Machine Learning and Deep Learning Models",
author = "Adyanthaya, Raksha and
P, Rathnakara Shetty",
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-1.50/",
doi = "10.18653/v1/2025.dravidianlangtech-1.50",
pages = "288--292",
ISBN = "979-8-89176-228-2",
abstract = "The sentiment analysis in code-mixed Dravidian languages such as Tamil-English and Tulu-English is the focus of this study because these languages present difficulties for conventional techniques. In this work, We used ensembles, multilingual Bidirectional Encoder Representation(mBERT), Bidirectional Long Short Term Memory (BiLSTM), Random Forest (RF), Support Vector Machine (SVM), and preprocessing in conjunction with Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec feature extraction. mBERT obtained accuracy of 64{\%} for Tamil and 68{\%} for Tulu on development datasets. In test sets, the ensemble model gave Tamil a macro F1-score of 0.4117, while mBERT gave Tulu a macro F1-score of 0.5511. With regularization and data augmentation, these results demonstrate the approach{'}s potential for further advancements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adyanthaya-p-2025-yenlp">
<titleInfo>
<title>YenLP_CS@DravidianLangTech 2025: Sentiment Analysis on Code-Mixed Tamil-Tulu Data Using Machine Learning and Deep Learning Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raksha</namePart>
<namePart type="family">Adyanthaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rathnakara</namePart>
<namePart type="given">Shetty</namePart>
<namePart type="family">P</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 sentiment analysis in code-mixed Dravidian languages such as Tamil-English and Tulu-English is the focus of this study because these languages present difficulties for conventional techniques. In this work, We used ensembles, multilingual Bidirectional Encoder Representation(mBERT), Bidirectional Long Short Term Memory (BiLSTM), Random Forest (RF), Support Vector Machine (SVM), and preprocessing in conjunction with Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec feature extraction. mBERT obtained accuracy of 64% for Tamil and 68% for Tulu on development datasets. In test sets, the ensemble model gave Tamil a macro F1-score of 0.4117, while mBERT gave Tulu a macro F1-score of 0.5511. With regularization and data augmentation, these results demonstrate the approach’s potential for further advancements.</abstract>
<identifier type="citekey">adyanthaya-p-2025-yenlp</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.50</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.50/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>288</start>
<end>292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YenLP_CS@DravidianLangTech 2025: Sentiment Analysis on Code-Mixed Tamil-Tulu Data Using Machine Learning and Deep Learning Models
%A Adyanthaya, Raksha
%A P, Rathnakara Shetty
%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 adyanthaya-p-2025-yenlp
%X The sentiment analysis in code-mixed Dravidian languages such as Tamil-English and Tulu-English is the focus of this study because these languages present difficulties for conventional techniques. In this work, We used ensembles, multilingual Bidirectional Encoder Representation(mBERT), Bidirectional Long Short Term Memory (BiLSTM), Random Forest (RF), Support Vector Machine (SVM), and preprocessing in conjunction with Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec feature extraction. mBERT obtained accuracy of 64% for Tamil and 68% for Tulu on development datasets. In test sets, the ensemble model gave Tamil a macro F1-score of 0.4117, while mBERT gave Tulu a macro F1-score of 0.5511. With regularization and data augmentation, these results demonstrate the approach’s potential for further advancements.
%R 10.18653/v1/2025.dravidianlangtech-1.50
%U https://aclanthology.org/2025.dravidianlangtech-1.50/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.50
%P 288-292
Markdown (Informal)
[YenLP_CS@DravidianLangTech 2025: Sentiment Analysis on Code-Mixed Tamil-Tulu Data Using Machine Learning and Deep Learning Models](https://aclanthology.org/2025.dravidianlangtech-1.50/) (Adyanthaya & P, DravidianLangTech 2025)
ACL