@inproceedings{yeshpanov-varol-2024-kazsandra-kazakh,
title = "{K}az{SA}n{DRA}: {K}azakh Sentiment Analysis Dataset of Reviews and Attitudes",
author = "Yeshpanov, Rustem and
Varol, Huseyin Atakan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.844",
pages = "9657--9667",
abstract = "This paper presents KazSAnDRA, a dataset developed for Kazakh sentiment analysis that is the first and largest publicly available dataset of its kind. KazSAnDRA comprises an extensive collection of 180,064 reviews obtained from various sources and includes numerical ratings ranging from 1 to 5, providing a quantitative representation of customer attitudes. The study also pursued the automation of Kazakh sentiment classification through the development and evaluation of four machine learning models trained for both polarity classification and score classification. Experimental analysis included evaluation of the results considering both balanced and imbalanced scenarios. The most successful model attained an F1-score of 0.81 for polarity classification and 0.39 for score classification on the test sets. The dataset and fine-tuned models are open access and available for download under the Creative Commons Attribution 4.0 International License (CC BY 4.0) through our GitHub repository.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeshpanov-varol-2024-kazsandra-kazakh">
<titleInfo>
<title>KazSAnDRA: Kazakh Sentiment Analysis Dataset of Reviews and Attitudes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rustem</namePart>
<namePart type="family">Yeshpanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huseyin</namePart>
<namePart type="given">Atakan</namePart>
<namePart type="family">Varol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents KazSAnDRA, a dataset developed for Kazakh sentiment analysis that is the first and largest publicly available dataset of its kind. KazSAnDRA comprises an extensive collection of 180,064 reviews obtained from various sources and includes numerical ratings ranging from 1 to 5, providing a quantitative representation of customer attitudes. The study also pursued the automation of Kazakh sentiment classification through the development and evaluation of four machine learning models trained for both polarity classification and score classification. Experimental analysis included evaluation of the results considering both balanced and imbalanced scenarios. The most successful model attained an F1-score of 0.81 for polarity classification and 0.39 for score classification on the test sets. The dataset and fine-tuned models are open access and available for download under the Creative Commons Attribution 4.0 International License (CC BY 4.0) through our GitHub repository.</abstract>
<identifier type="citekey">yeshpanov-varol-2024-kazsandra-kazakh</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.844</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9657</start>
<end>9667</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KazSAnDRA: Kazakh Sentiment Analysis Dataset of Reviews and Attitudes
%A Yeshpanov, Rustem
%A Varol, Huseyin Atakan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yeshpanov-varol-2024-kazsandra-kazakh
%X This paper presents KazSAnDRA, a dataset developed for Kazakh sentiment analysis that is the first and largest publicly available dataset of its kind. KazSAnDRA comprises an extensive collection of 180,064 reviews obtained from various sources and includes numerical ratings ranging from 1 to 5, providing a quantitative representation of customer attitudes. The study also pursued the automation of Kazakh sentiment classification through the development and evaluation of four machine learning models trained for both polarity classification and score classification. Experimental analysis included evaluation of the results considering both balanced and imbalanced scenarios. The most successful model attained an F1-score of 0.81 for polarity classification and 0.39 for score classification on the test sets. The dataset and fine-tuned models are open access and available for download under the Creative Commons Attribution 4.0 International License (CC BY 4.0) through our GitHub repository.
%U https://aclanthology.org/2024.lrec-main.844
%P 9657-9667
Markdown (Informal)
[KazSAnDRA: Kazakh Sentiment Analysis Dataset of Reviews and Attitudes](https://aclanthology.org/2024.lrec-main.844) (Yeshpanov & Varol, LREC-COLING 2024)
ACL