TY - GEN

T1 - Utilizing Lexicographic Resources for Sentiment Classification in Uzbek Language

AU - Mengliev, Davlatyor B.

AU - Akhmedov, Ergash Yu.

AU - Barakhnin, Vladimir B.

AU - Hakimov, Zohid A.

AU - Alloyorov, Oybek M.

N1 - Conference code: 16

PY - 2023

Y1 - 2023

N2 - Nowadays it is seen the active development of text sentiment analysis tools, which help solve a huge range of problems, ranging from emotional tone or polarity to the nature of the analyzed text. Although significant advances have been made in sentiment analysis for languages with abundant computing resources, the problem still remains relevant for resource-poor languages, where Uzbek is one of them. The lack of complete linguistic databases and tools for this language represents a major obstacle for the scientific community. The present study aims to address this limitation by introducing a rule-based approach for sentiment analysis in the Uzbek language. In particular, the methodology uses three key vocabularies: the first includes a comprehensive list of more than 300 affixes used to generate word forms; the second focuses on cataloging exception words that defy standard morphological rules; and the third contains a list of word roots, some of the word roots are already marked with positive or negative sentiment polarity. When combined, morphological analysis with these lexical resources can effectively recognize tonal orientation in Uzbek sentences. This is especially important given the agglutinative nature of language and complex morphological structures that add layers of subtle meaning, influencing the interpretation of sentiments.

AB - Nowadays it is seen the active development of text sentiment analysis tools, which help solve a huge range of problems, ranging from emotional tone or polarity to the nature of the analyzed text. Although significant advances have been made in sentiment analysis for languages with abundant computing resources, the problem still remains relevant for resource-poor languages, where Uzbek is one of them. The lack of complete linguistic databases and tools for this language represents a major obstacle for the scientific community. The present study aims to address this limitation by introducing a rule-based approach for sentiment analysis in the Uzbek language. In particular, the methodology uses three key vocabularies: the first includes a comprehensive list of more than 300 affixes used to generate word forms; the second focuses on cataloging exception words that defy standard morphological rules; and the third contains a list of word roots, some of the word roots are already marked with positive or negative sentiment polarity. When combined, morphological analysis with these lexical resources can effectively recognize tonal orientation in Uzbek sentences. This is especially important given the agglutinative nature of language and complex morphological structures that add layers of subtle meaning, influencing the interpretation of sentiments.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85182262535&origin=inward&txGid=35d12795f2b96d2541ecaea5a4b515ff

UR - https://www.mendeley.com/catalogue/602194cb-6302-34d2-b165-816e1b22b9b1/

U2 - 10.1109/apeie59731.2023.10347765

DO - 10.1109/apeie59731.2023.10347765

M3 - Conference contribution

SN - 9798350330885

SP - 1720

EP - 1724

BT - Proceedings of the 2023 IEEE 16th International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering, APEIE 2023

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 16th IEEE International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering

Y2 - 10 November 2023 through 12 November 2023

ER -