@inproceedings{krasitskii-etal-2025-advancing,
title = "Advancing Sentiment Analysis in {T}amil-{E}nglish Code-Mixed Texts: Challenges and Transformer-Based Solutions",
author = "Krasitskii, Mikhail and
Kolesnikova, Olga and
Chanona Hernandez, Liliana and
Sidorov, Grigori and
Gelbukh, Alexander",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.27/",
doi = "10.18653/v1/2025.nlp4dh-1.27",
pages = "305--312",
ISBN = "979-8-89176-234-3",
abstract = "This study examines sentiment analysis in Tamil-English code-mixed texts using advanced transformer-based architectures. The unique linguistic challenges, including mixed grammar, orthographic variability, and phonetic inconsistencies, are addressed. Data limitations and annotation gaps are discussed, highlighting the need for larger datasets. The performance of models such as XLM-RoBERTa, mT5, IndicBERT, and RemBERT is evaluated, with insights into their optimization for low-resource, code-mixed environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krasitskii-etal-2025-advancing">
<titleInfo>
<title>Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Krasitskii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kolesnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liliana</namePart>
<namePart type="family">Chanona Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</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 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>This study examines sentiment analysis in Tamil-English code-mixed texts using advanced transformer-based architectures. The unique linguistic challenges, including mixed grammar, orthographic variability, and phonetic inconsistencies, are addressed. Data limitations and annotation gaps are discussed, highlighting the need for larger datasets. The performance of models such as XLM-RoBERTa, mT5, IndicBERT, and RemBERT is evaluated, with insights into their optimization for low-resource, code-mixed environments.</abstract>
<identifier type="citekey">krasitskii-etal-2025-advancing</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.27</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.27/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>305</start>
<end>312</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions
%A Krasitskii, Mikhail
%A Kolesnikova, Olga
%A Chanona Hernandez, Liliana
%A Sidorov, Grigori
%A Gelbukh, Alexander
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F krasitskii-etal-2025-advancing
%X This study examines sentiment analysis in Tamil-English code-mixed texts using advanced transformer-based architectures. The unique linguistic challenges, including mixed grammar, orthographic variability, and phonetic inconsistencies, are addressed. Data limitations and annotation gaps are discussed, highlighting the need for larger datasets. The performance of models such as XLM-RoBERTa, mT5, IndicBERT, and RemBERT is evaluated, with insights into their optimization for low-resource, code-mixed environments.
%R 10.18653/v1/2025.nlp4dh-1.27
%U https://aclanthology.org/2025.nlp4dh-1.27/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.27
%P 305-312
Markdown (Informal)
[Advancing Sentiment Analysis in Tamil-English Code-Mixed Texts: Challenges and Transformer-Based Solutions](https://aclanthology.org/2025.nlp4dh-1.27/) (Krasitskii et al., NLP4DH 2025)
ACL