@inproceedings{krasitskii-etal-2024-multilingual,
title = "Multilingual Approaches to Sentiment Analysis of Texts in Linguistically Diverse Languages: A Case Study of {F}innish, {H}ungarian, and {B}ulgarian",
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
Pirinen, Flammie and
Macias, Melany and
Crespo Avila, Mario},
booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",
month = nov,
year = "2024",
address = "Helsinki, Finland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwclul-1.6",
pages = "49--58",
abstract = "This article is dedicated to the study of multilingual approaches to sentiment analysis of texts in Finnish, Hungarian, and Bulgarian. For Finnish and Hungarian, which are characterized by complex morphology and agglutinative grammar, an analysis was conducted using both traditional rule-based methods and modern machine learning techniques. In the study, BERT, XLM-R, and mBERT models were used for sentiment analysis, demonstrating high accuracy in sentiment classification. The inclusion of Bulgarian was motivated by the opportunity to compare results across languages with varying degrees of morphological complexity, which allowed for a better understanding of how these models can adapt to different linguistic structures. Datasets such as the Hungarian Emotion Corpus, FinnSentiment, and SentiFi were used to evaluate model performance. The results showed that transformer-based models, particularly BERT, XLM-R, and mBERT, significantly outperformed traditional methods, achieving high accuracy in sentiment classification tasks for all the languages studied.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krasitskii-etal-2024-multilingual">
<titleInfo>
<title>Multilingual Approaches to Sentiment Analysis of Texts in Linguistically Diverse Languages: A Case Study of Finnish, Hungarian, and Bulgarian</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>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages</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">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melany</namePart>
<namePart type="family">Macias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Crespo Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Helsinki, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article is dedicated to the study of multilingual approaches to sentiment analysis of texts in Finnish, Hungarian, and Bulgarian. For Finnish and Hungarian, which are characterized by complex morphology and agglutinative grammar, an analysis was conducted using both traditional rule-based methods and modern machine learning techniques. In the study, BERT, XLM-R, and mBERT models were used for sentiment analysis, demonstrating high accuracy in sentiment classification. The inclusion of Bulgarian was motivated by the opportunity to compare results across languages with varying degrees of morphological complexity, which allowed for a better understanding of how these models can adapt to different linguistic structures. Datasets such as the Hungarian Emotion Corpus, FinnSentiment, and SentiFi were used to evaluate model performance. The results showed that transformer-based models, particularly BERT, XLM-R, and mBERT, significantly outperformed traditional methods, achieving high accuracy in sentiment classification tasks for all the languages studied.</abstract>
<identifier type="citekey">krasitskii-etal-2024-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.iwclul-1.6</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>49</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Approaches to Sentiment Analysis of Texts in Linguistically Diverse Languages: A Case Study of Finnish, Hungarian, and Bulgarian
%A Krasitskii, Mikhail
%A Kolesnikova, Olga
%A Chanona Hernandez, Liliana
%A Sidorov, Grigori
%A Gelbukh, Alexander
%Y Hämäläinen, Mika
%Y Pirinen, Flammie
%Y Macias, Melany
%Y Crespo Avila, Mario
%S Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages
%D 2024
%8 November
%I Association for Computational Linguistics
%C Helsinki, Finland
%F krasitskii-etal-2024-multilingual
%X This article is dedicated to the study of multilingual approaches to sentiment analysis of texts in Finnish, Hungarian, and Bulgarian. For Finnish and Hungarian, which are characterized by complex morphology and agglutinative grammar, an analysis was conducted using both traditional rule-based methods and modern machine learning techniques. In the study, BERT, XLM-R, and mBERT models were used for sentiment analysis, demonstrating high accuracy in sentiment classification. The inclusion of Bulgarian was motivated by the opportunity to compare results across languages with varying degrees of morphological complexity, which allowed for a better understanding of how these models can adapt to different linguistic structures. Datasets such as the Hungarian Emotion Corpus, FinnSentiment, and SentiFi were used to evaluate model performance. The results showed that transformer-based models, particularly BERT, XLM-R, and mBERT, significantly outperformed traditional methods, achieving high accuracy in sentiment classification tasks for all the languages studied.
%U https://aclanthology.org/2024.iwclul-1.6
%P 49-58
Markdown (Informal)
[Multilingual Approaches to Sentiment Analysis of Texts in Linguistically Diverse Languages: A Case Study of Finnish, Hungarian, and Bulgarian](https://aclanthology.org/2024.iwclul-1.6) (Krasitskii et al., IWCLUL 2024)
ACL