sibsutisВестник СибГУТИThe Herald of the Siberian State University of Telecommunications and Information Science1998-6920СибГУТИ10.55648/1998-6920-2026-20-1-23-38sibsutis-1041Research ArticleСтатьиПрограммный комплекс для гибридного анализа тональности узбекских текстов с использованием именованных сущностейSoftware System for Hybrid Sentiment Analysis of Uzbek Texts using Named Entitieshttps://orcid.org/0009-0000-5540-2013СаидовБобур РашидовичSaidovBobur Rashidovich

аспирант НГУ

PhD student

b.saidov@g.nsu.ruhttps://orcid.org/0000-0003-3299-0507БарахнинВладимир БорисовичBarakhninVladimir Borisovich

доктор технических наук, доцент НГУ

Doctor of Technical Sciences, Associate Professor

v.barakhnin@g.nsu.ruНовосибирский национальный исследовательский государственный университетРоссияNovosibirsk State UniversityRussian FederationФедеральный исследовательский центр информационных и вычислительных технологий; Сибирский государственный университет телекоммуникаций и информатики (СибГУТИ)РоссияFederal Research Center for Information and Computational Technologies; Siberian State University of Telecommunications and Information Science (SibSUTIS)Russian Federation202627032026201Вестник СибГУТИ2338Copyright © Саидов Б.Р., Барахнин В.Б., 20262026Саидов Б.Р., Барахнин В.Б.Saidov B.R., Barakhnin V.B.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.sibsutis.ru/jour/article/view/1041

 В данной статье представлен программный комплекс для автоматическогоанализа тональности узбекских текстов. Система основана на гибридном подходе, сочетающем модель трансформатора, модуль извлечения именованных сущностей (NER) и специально составленный словарь тональности узбекского языка. Актуальность даннойразработки обусловлена растущим объемом неформальных текстов в социальных сетях и отсутствием готовых инструментов для их обработки. Комплекс реализует полный цикл обработки: очистку и нормализацию текста, извлечение сущностей, определение тональности и ключевых слов, а также визуализацию результатов во встроенном вебинтерфейсе. Модели и словарь адаптированы к агглютинативным и орфографическимособенностям узбекского языка, что повышает устойчивость к разговорной и смешанной письменности. Кратко описаны архитектура комплекса, основные программные модули иих взаимодействие, а также принцип работы прикладного интерфейса (REST API). Приведены примеры использования системы для анализа отзывов и сообщений пользователей, подтверждающие её пригодность для решения прикладных задач мониторинга общественного мнения. По результатам первоначальных экспериментов достигнуто существенное улучшение качества по сравнению с базовыми моделями текстабез учета НЭР и лексики.

This article presents a software package for automatic sentiment analysis of Uzbek texts. The system relies on a hybrid approach, combining a transformer model, a named entity extraction (NER) module, and a specially compiled sentiment dictionary of the Uzbek language. The relevance of this development is due to the growing volume of informal texts on social networks and the lack of ready-made tools for processing them. The package implements a full processing cycle: text cleaning and normalization, entity extraction, sentiment detection and keyword detection, and visualization of the results in a built-in web interface. The models and dictionary are adapted to the agglutinative and orthographic features of the Uzbek language, increasing resilience to colloquial and mixed forms of writing. The package's architecture, main software modules and their interactions, as well as the operating principle of the application interface (REST API) are briefly described. Examples of the system's application for analyzing user reviews and messages are provided, confirming its suitability for applied opinion monitoring tasks. Based on the results of initial experiments, a significant improvement in quality is achieved compared to basic text models without taking into account NER and lexicon.

анализ тональностиузбекский языкизвлечение именованных сущностейэмоциональный словарьгибридная модельпрограммный комплексsentiment analysisUzbek languagenamed entity recognitionemotion lexiconhybrid modelsoftware systemИсследование выполнено в рамках государственного задания Министерства науки и высшего образования Российской Федерации для Федерального исследовательского центра информационных и вычислительных технологий.The research was carried out within the state assignment of Ministry of Science and Higher Education of the Russian Federation for Federal Research Center for Information and Computational Technologies.ReferencesKuriyozov E., Salaev U., Matlatipov S., Matlatipov G. Text classification dataset and analysis for Uzbek language. arXiv preprint arXiv:2302.14494, 2023.Kuriyozov E., Salaev U., Matlatipov S., Matlatipov G. Text classification dataset and analysis for Uzbek language. arXiv:2302.14494, 2023. DOI:10.5281/zenodo.7677431DOI: 10.5281/zenodo.7677431.Matlatipov S., Rahimboeva H., Rajabov J., Kuriyozov E. Uzbek Sentiment Analysis Based on Local Restaurant Reviews. In: Proc. ALTNLP Workshop, 2022. DOI:10.48550/arXiv.2205.15930Matlatipov S., Rahimboeva H., Rajabov J., Kuriyozov E. Uzbek Sentiment Analysis Based on Local Restaurant Reviews. In: Proceedings of the ALTNLP Workshop. 2022. DOI:10.48550/arXiv.2205.15930.Matlatipov S., Rajabov J., Kuriyozov E., Aripov M. UzABSA: Aspect-Based Sentiment Analysis for the Uzbek Language. In: Proc. SIGUL 2024 – 3rd Workshop on Speech and Language Technologies for Low-Resource Languages, 2024.Matlatipov S., Rajabov J., Kuriyozov E., Aripov M. UzABSA: Aspect-Based Sentiment Analysis for the Uzbek Language. In: Proceedings of SIGUL 2024 – 3rd Workshop on Speech and Language Technologies for Low-Resource Languages. 2024.Kuriyozov E., Vilares D., Gómez-Rodríguez C. BERTbek: A Pretrained Language Model for Uzbek. In: Proc. SIGUL 2024, pp. 33–44, 2024Kuriyozov E., Vilares D., Gómez-Rodríguez C. BERTbek: A Pretrained Language Model for Uzbek. In: Proceedings of SIGUL 2024. 2024. P. 33–44.Tan K. L., Lee C. P., Lim K. M. A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research. Applied Sciences, 13(7), 4550, 2023. DOI: 10.3390/app13074550.Tan K. L., Lee C. P., Lim K. M. A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research. Applied Sciences, 2023, vol. 13, no. 7, 4550.Nip J. Y. M. Social Media Sentiment Analysis. Encyclopedia, 4(4), Art. 104, 2024.DOI: 10.3390/app13074550.DOI: 10.3390/encyclopedia4040104Nip J. Y. M. Social Media Sentiment Analysis. Encyclopedia, 2024, vol. 4, no. 4, 104. DOI:10.3390/encyclopedia4040104.Aftab F., Bazai S. U., et al. A Comprehensive Survey on Sentiment Analysis Techniques. International Journal of Technology, 14(6), 2023. DOI: 10.14716/ijtech.v14i6.6632.Aftab F., Bazai S. U., et al. A Comprehensive Survey on Sentiment AnalysisAliyu M. A., Ibrahim F., Musa A., et al. A Systematic Review of Sentiment Analysis in Low-Resource Languages. IEEE Access, 12, 2024. DOI:10.1109/ACCESS.2024.3398635Techniques. International Journal of Technology, 2023, vol. 14, no. 6.[9] Mengliev D., Abdurakhmonova N., Shirinova R., Suyunova M. Developing Named Entity Recognition Algorithms for Uzbek: Dataset Insights and Implementation. Data in Brief, 54, 110413, 2024. DOI:10.1016/j.dib.2024.110413DOI: 10.14716/ijtech.v14i6.6632.Saidov B. R., Barakhnin V. B., Rixsibayev U. T., Sharipov E. J. Methods of Automatic Selection of Named Entities (NER) in Uzbek Language for Text Tone Analysis. Conference paper, 2025.Aliyu M. A., Ibrahim F., Musa A., et al. A Systematic Review of Sentiment Analysis in Low-Resource Languages. IEEE Access, 2024, vol. 12.Saidov B. R., et al. Creating an Emotional Dictionary for the Uzbek Language: Taking Cultural–Linguistic Specifics into Account. 2024/2025.DOI: 10.1109/ACCESS.2024.3398635.Saidov B. R., et al. Sentiment Analysis of Uzbek Texts Using NER: A omparative Study of SVM, LSTM and BERT Models. Vestnik SibGUTI, 2025 (в печати).Mengliev D., Abdurakhmonova N., Shirinova R., Suyunova M. Developing Named Entity Recognition Algorithms for Uzbek: Dataset Insights and Implementation. Data in Brief, 2024, vol. 54, 110413. DOI: 10.1016/j.dib.2024.110413.Atlas L. G. et al. A modernized approach to sentiment analysis of product reviews using BiGRU and RNN based LSTM deep learning models. Scientific Reports, 15, 6642, 2025. DOI: 10.1038/s41598-025-01104-0Saidov B. R., Barakhnin V. B., Rixsibayev U. T., Sharipov E. J. Methods of Automatic Selection of Named Entities (NER) in Uzbek Language for Text Tone Analysis. In: Proceedings of the International Conference on Computational Linguistics and Intelligent Systems. 2025.Chhetri G., Dutta A., Das S. CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media. arXiv preprint, 2025. DOI:10.48550/arXiv.2509.11444.B. R. Saidov, V. B. Barakhnin 37Islam T. et al. Lexicon and Deep Learning-Based Approaches in Sentiment Analysis on Short Texts. Journal of Computer and Communications, 12(1), 11–34, 2024.Saidov B. R., et al. Creating an Emotional Dictionary for the Uzbek Language: Taking Cultural–Linguistic Specifics into Account. Journal of Language Resources and Evaluation, 2025, vol. 59, no. 2, pp. 245–268.DOI: 10.4236/jcc.2024.121002Saidov B. R., et al. Sentiment Analysis of Uzbek Texts Using NER: A Comparative Study of SVM, LSTM, and BERT Models. Vestnik SibGUTI, 2025, vol. 19, no. 4, (in press).Tang X. et al. EMFSA: Emoji-based multifeature fusion sentiment analysis. PLOS ONE, 19(9): e0311415, 2024. DOI: 10.1371/journal.pone.0311415Atlas L. G., et al. A modernized approach to sentiment analysis of product reviews using BiGRU and RNN based LSTM deep learning models. Scientific Reports, 2025, vol. 15, 6642. DOI: 10.1038/s41598-025-01104-0.Sufi F. K. AI approach on identifying change in public sentiment for major events: Dubai Expo 2020. Journal of Engineering Research, 2024.Chhetri G., Dutta A., Das S. CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media. arXiv preprint arXiv:2509.11444, 2025.DOI: 10.1016/j.jer.2024.07.010DOI: 10.48550/arXiv.2509.11444.Hash Block. Real-Time Sentiment Analysis App with NestJS Backend and Streamlit Frontend. Medium, 11 July 2025.Islam T., et al. Lexicon and Deep Learning-Based Approaches in Sentiment Analysis on Short Texts. Journal of Computer and Communications, 2024, vol. 12, no. 1, pp. 11–34. DOI: 10.4236/jcc.2024.121002.Seow W. L., Chaturvedi I., Hogarth A., Mao R., Cambria E. A review of named entity recognition: from learning methods to modelling paradigms and tasks. Artificial Intelligence Review, 58, 315, 2025.Tang X., et al. EMFSA: Emoji-based multifeature fusion sentiment analysis. PLOS ONE, 2024, vol. 19, no. 9, e0311415. DOI: 10.1371/journal.pone.0311415.DOI: 10.1007/s10462-025-11321-8Sufi F. K. AI approach on identifying change in public sentiment for major events: Dubai Expo 2020. Journal of Engineering Research, 2024. DOI: 10.1016/j.jer.2024.07.010.Veitsman Y., Hartmann M. Recent Advancements and Challenges of Turkic Central Asian Language Processing. In: Proc. First Workshop on Language Models for Low-Resource Languages (LoResLM), 2025; также arXiv:2407.05006.Hash Block. Real-Time Sentiment Analysis App with NestJS Backend and Streamlit Frontend. Medium, 11 July 2025. Available at: https://medium.com/...DOI: 10.48550/arXiv.2407.05006Seow W. L., Chaturvedi I., Hogarth A., Mao R., Cambria E. A review of named entity recognition: from learning methods to modelling paradigms and tasks. Artificial Intelligence Review, 2025, vol. 58, 315. DOI: 10.1007/s10462-025-11321-8.Seow W. L., Chaturvedi I., Hogarth A., Mao R., Cambria E. A review of named entity recognition: from learning methods to modelling paradigms and tasks. Artificial Intelligence Review, 2025, vol. 58, 315. DOI: 10.1007/s10462-025-11321-8.Veitsman Y., Hartmann M. Recent Advancements and Challenges of Turkic Central Asian Language Processing. In: Proceedings of the First Workshop on Language Models for LowResource Languages (LoResLM), 2025. DOI: 10.48550/arXiv.2407.05006.Veitsman Y., Hartmann M. Recent Advancements and Challenges of Turkic Central Asian Language Processing. In: Proceedings of the First Workshop on Language Models for LowResource Languages (LoResLM), 2025. DOI: 10.48550/arXiv.2407.05006.Saidov B. R., Barakhnin V. B., Madirimov Sh., Ibragimov U., Meylikulov Sh., Normamatov S., Bahodirova F., Matnazarov J., Fayzullaeva Z. Dual-Source Synthetic Uzbek Corpora for Sentiment Analysis and NER with Controlled Emoji Signals. Data, 2026, vol. 11, no. 2, 28. DOI: 10.3390/data11020028.Saidov B. R., Barakhnin V. B., Madirimov Sh., Ibragimov U., Meylikulov Sh., Normamatov S., Bahodirova F., Matnazarov J., Fayzullaeva Z. Dual-Source Synthetic Uzbek Corpora for Sentiment Analysis and NER with Controlled Emoji Signals. Data, 2026, vol. 11, no. 2, 28. DOI: 10.3390/data11020028.Saidov B. R., Barakhnin V. B., et al. Methods of Automatic Selection of Named Entities (NER) in Uzbek Language for Text Tone Analysis. In: Proceedings of the IEEE 26th International Conference of Young Professionals in Electron Devices and Materials (EDM-2025). Altai, Russian Federation, 2025. DOI: 10.1109/EDM65517.2025.11096748.Saidov B. R., Barakhnin V. B., et al. Methods of Automatic Selection of Named Entities (NER) in Uzbek Language for Text Tone Analysis. In: Proceedings of the IEEE 26th International Conference of Young Professionals in Electron Devices and Materials (EDM-2025). Altai, Russian Federation, 2025. DOI: 10.1109/EDM65517.2025.11096748.Saidov B. R., et al. Integration of a Sentiment Dictionary and NER System into a Tool for Analyzing Public Opinion in the Uzbek Language. In: Proceedings of the IEEE 2025 International Conference AL-KHWARIZMI (APEIE-2025). Urgench, Uzbekistan, 2025. DOI: 10.1109/APEIE66761.2025.11289303.Saidov B. R., et al. Integration of a Sentiment Dictionary and NER System into a Tool for Analyzing Public Opinion in the Uzbek Language. In: Proceedings of the IEEE 2025 International Conference AL-KHWARIZMI (APEIE-2025). Urgench, Uzbekistan, 2025. DOI: 10.1109/APEIE66761.2025.11289303.

The authors declare that there are no conflicts of interest present.