@inproceedings{eusha-etal-2024-cuet,
title = "{CUET}{\_}{B}inary{\_}{H}ackers@{D}ravidian{L}ang{T}ech-{EACL} 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated {T}amil and {T}ulu",
author = "Eusha, Asrarul and
Farsi, Salman and
Islam, Ariful and
Hossain, Jawad and
Ahsan, Shawly and
Hoque, Mohammed Moshiul",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Nadarajan, Rajeswari and
Ravikiran, Manikandan",
booktitle = "Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.dravidianlangtech-1.34",
pages = "205--211",
abstract = "Textual Sentiment Analysis (TSA) delves into people{'}s opinions, intuitions, and emotions regarding any entity. Natural Language Processing (NLP) serves as a technique to extract subjective knowledge, determining whether an idea or comment leans positive, negative, neutral, or a mix thereof toward an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of online comments and opinions. Despite extensive studies in this domain, sentiment analysis in low-resourced languages such as Tamil and Tulu needs help handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explored four machine learning (ML) approaches (LR, SVM, XGBoost, Ensemble), four deep learning (DL) methods (BiLSTM and CNN with FastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and Distilm-BERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperformed others, while m-BERT demonstrated superior performance among the models for Tulu. The presented models achieved the $3^{rd}$ and $1^{st}$ ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eusha-etal-2024-cuet">
<titleInfo>
<title>CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asrarul</namePart>
<namePart type="family">Eusha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Farsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariful</namePart>
<namePart type="family">Islam</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">Shawly</namePart>
<namePart type="family">Ahsan</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>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth 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">Rajeswari</namePart>
<namePart type="family">Nadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manikandan</namePart>
<namePart type="family">Ravikiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Textual Sentiment Analysis (TSA) delves into people’s opinions, intuitions, and emotions regarding any entity. Natural Language Processing (NLP) serves as a technique to extract subjective knowledge, determining whether an idea or comment leans positive, negative, neutral, or a mix thereof toward an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of online comments and opinions. Despite extensive studies in this domain, sentiment analysis in low-resourced languages such as Tamil and Tulu needs help handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explored four machine learning (ML) approaches (LR, SVM, XGBoost, Ensemble), four deep learning (DL) methods (BiLSTM and CNN with FastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and Distilm-BERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperformed others, while m-BERT demonstrated superior performance among the models for Tulu. The presented models achieved the 3^rd and 1^st ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.</abstract>
<identifier type="citekey">eusha-etal-2024-cuet</identifier>
<location>
<url>https://aclanthology.org/2024.dravidianlangtech-1.34</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>205</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu
%A Eusha, Asrarul
%A Farsi, Salman
%A Islam, Ariful
%A Hossain, Jawad
%A Ahsan, Shawly
%A Hoque, Mohammed Moshiul
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Nadarajan, Rajeswari
%Y Ravikiran, Manikandan
%S Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F eusha-etal-2024-cuet
%X Textual Sentiment Analysis (TSA) delves into people’s opinions, intuitions, and emotions regarding any entity. Natural Language Processing (NLP) serves as a technique to extract subjective knowledge, determining whether an idea or comment leans positive, negative, neutral, or a mix thereof toward an entity. In recent years, it has garnered substantial attention from NLP researchers due to the vast availability of online comments and opinions. Despite extensive studies in this domain, sentiment analysis in low-resourced languages such as Tamil and Tulu needs help handling code-mixed and transliterated content. To address these challenges, this work focuses on sentiment analysis of code-mixed and transliterated Tamil and Tulu social media comments. It explored four machine learning (ML) approaches (LR, SVM, XGBoost, Ensemble), four deep learning (DL) methods (BiLSTM and CNN with FastText and Word2Vec), and four transformer-based models (m-BERT, MuRIL, L3Cube-IndicSBERT, and Distilm-BERT) for both languages. For Tamil, L3Cube-IndicSBERT and ensemble approaches outperformed others, while m-BERT demonstrated superior performance among the models for Tulu. The presented models achieved the 3^rd and 1^st ranks by attaining macro F1-scores of 0.227 and 0.584 in Tamil and Tulu, respectively.
%U https://aclanthology.org/2024.dravidianlangtech-1.34
%P 205-211
Markdown (Informal)
[CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu](https://aclanthology.org/2024.dravidianlangtech-1.34) (Eusha et al., DravidianLangTech-WS 2024)
ACL
- Asrarul Eusha, Salman Farsi, Ariful Islam, Jawad Hossain, Shawly Ahsan, and Mohammed Moshiul Hoque. 2024. CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu. In Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 205–211, St. Julian's, Malta. Association for Computational Linguistics.