Development of a mathematical model for the processes of researching citizen appeals
Elena Nikolaevna Vanchikova,
Alexander Nikolaevich Timofeev,
Nima Batodorzhievich Saduev,
Elena Ochirovna Vanzatova https://doi.org/10.55648/1998-6920-2026-20-1-39-56
Abstract
Currently, citizens actively participate in public discussions that affect the life of society. With the development of digitalization, users are increasingly using social networks and feedback platforms (FBPs) to express their opinions on various areas of activity. In this regard, there is a need to analyze public sentiment using modern analytical tools in order to identify
potential problems at an early stage. This article describes the development of a mathematical model for analyzing public sentiment based on text messages published on social networks and other sources. The model includes data preprocessing, clustering of requests, naming of clusters using language models, and summarization of identified problems.
Keywords
mathematical model, machine learning, neural networks, public appeals, and public sentiment analysis
Supporting agencies: Работа выполнена при финансовой поддержке республиканского бюджета Республики Бурятия, проект №25-28-20352 «Применение методов машинного обучения для оценки эффективности реализации проектов по программе «Комплексное развитие сельских территорий на основе мониторинга изменений актуальных проблем сельских жителей» и НИР «Построение математической модели для исследования общественных настроений их текстовых сообщений, опубликованных в социальных сетях на основе цифровых следов жителей Республики Бурятия».
About the Authors
Elena Nikolaevna Vanchikova
Buryat State Agricultural Academy named after V.R. Filippova
Russian Federation
Russian Federation
Dr of Economics, Professor of the Department of Management
Alexander Nikolaevich Timofeev
SibDigital LLC
Russian Federation
Russian Federation
General Director
Nima Batodorzhievich Saduev
Buryat State Agricultural Academy named after V.R. Filippova
Russian Federation
Russian Federation
PhD, Associate Professor of the Department of Informatics and Information Technologies in Economics
Elena Ochirovna Vanzatova
Buryat State Agricultural Academy named after V.R. Filippova
Russian Federation
Russian Federation
Candidate of Economics, Associate Professor of the Department of Informatics and Information
Technologies in Economics
References
1. Algorithm Recommendation and Performance Prediction Using Meta-Learning / G. Palumbo, D. Carneiro, M. Guimares [et al.] // International Journal of Neural Systems. – 2023. – Vol. 33, No. 03. – DOI 10.1142/s0129065723500119. – EDN BKIHSA.
2. Brown T. B. et al. Language Models are Few-Shot Learners // Advances in Neural Infor-mation Processing Systems (NeurIPS). – 2020. – Vol. 33. – P. 1877–1901. – URL: https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf (дата обращения: 10.10.2025).
3. Bunova E.V., Serova V.S. METHODOLOGY FOR SOLVING PROBLEMS OF CLASSIFICATION OF APPEALS/REQUESTS OF CITIZENS TO THE “HOTLINE” OF THE PRESIDENT OF THE RUSSIAN FEDERATION // Вестник ЮУрГУ. Серия: Компьютерные тех-нологии, управление, радиоэлектроника. 2022. №2. URL: https://cyberleninka.ru/article/n/methodology-for-solving-problems-of-classification-of-appeals-requests-of-citizens-to-the-hotline-of-the-president-of-the-russian (дата обращения: 01.10.2025).
4. Crossley, N. Social Networks of Meaning and Communication / N. Crossley // American Journal of Sociology. – 2023. – Vol. 128, No. 6. – P. 1849-1851. – DOI 10.1086/723877. – EDN JSOZHD.
5. Development of and research on machine learning algorithms for solving the classification problem in Twitter publications / I. S. Makarov, E. R. Bagantsova, P. A. Iashin [et al.] // Computer Research and Modeling. – 2023. – Vol. 15, No. 1. – P. 185-195. – DOI 10.20537/2076-7633-2023-15-1-185-195. – EDN WWFPKJ.
6. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo-gies (NAACL-HLT). – 2019. – Vol. 1. – P. 4171–4186. – DOI: 10.18653/v1/N19-1423.
7. Dildora Kabulovna Muhamediyeva, Nigora Nurmaxamadovna Abdurakhmanova, Nilufar Sirojidinovna Mirzayeva USING CONVENTIONAL NEURAL NETWORKS FOR THE PROBLEM OF TEXT CLASSIFICATION // Central Asian Academic Journal of Scientific Research. 2021. №1. URL: https://cyberleninka.ru/article/n/using-conventional-neural-networks-for-the-problem-of-text-classification (дата обращения: 15.10.2025).
8. LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Net-works / L. Zhang, Yu. Hu, W. Li [et al.] // Systems. – 2025. – Vol. 13, No. 1. – P. 29. – DOI 10.3390/systems13010029. – EDN QNDVCX. Scopus
9. Lukai Wang, Lei Wang. A Case Study of Chinese Sentiment Analysis of Social Media Re-views Based on LSTM // SHS Web of Conferences 157, 04012 (2023). – URL: https://doi.org/10.1051/shsconf/202315704012 (дата обращения: 01.12.2025).
10. Narang Kim, Soongoo Hong. Automatic classification of citizen requests for transporta-tion using deep learning: Case study from Boston city, Information Processing & Manage-ment,Volume 58, Issue 1, 2021, 102410, ISSN 0306-4573. URL: https://doi.org/10.1016/j.ipm.2020.102410
11. Ritushree Narayan, Pintu Samanta. A Machine Learning Approach for Sentiment Analysis Using Social Media Posts // International Journal of Information Technology and Computer Sci-ence. 2024. – 5 Vol. 16. – P. 23-35. - DOI: 10.5815/ijitcs.2024.05.02
12. Robert M. Cronin, Daniel Fabbri and Joshua C. Denny et al. A comparison of rule-based and machine learning approaches for classifying patient portal messages. Int J Med Inform. 2017. Vol. 105:110-120. - DOI: 10.1016/j.ijmedinf.2017.06.004
13. Tolebay A.N. SENTIMENT ANALYSIS OF TEXTS FROM SOCIAL NETWORKS BASED ON MACHINE LEARNING METHODS FOR MONITORING PUBLIC SENTIMENT // Bulletin of Science. 2025. №4 (85). URL: https://cyberleninka.ru/article/n/sentiment-analysis-of-texts-from-social-networks-based-on-machine-learning-methods-for-monitoring-public-sentiment (дата обращения: 05.12.2025).
14. Yang Y F and Zhou H, Zhou B. Data clustering based on the modified relaxation Cheeger cut model. Computational and Applied Mathematics, 2022, 41(1): 55–62.
15. Anokhina, I. Yu. Clustering of VKontakte Social Network Communities / I. Yu. Anokhina, E. V. Roshchina // Informatics and Cybernetics. – 2018. – No. 2(12). – Pp. 34-42. – EDN UGDRUA.
16. Evdoshenko Oleg Igorevich, Evdoshenko Nailya Ilnurovna DEVELOPMENT OF AN AUTOMATIC CLASSIFIER MODEL FOR CITIZENS' APPEALS // Caspian Journal: Management and High Technologies. 2024. No. 2 (66). URL: https://cyberleninka.ru/article/n/razrabotka-modeli-avtomaticheskogo-klassifikatora-obrashcheniy-grazhdan (accessed: 07.12.2025).
17. Martyshkin, A. I. Opportunities for Identifying the Emotional State of Social Media Users Using Machine Learning Methods / A. I. Martyshkin, V. S. Britov, and Yu. R. Drozdova // Modern Information Technologies. – 2024. – No. 40(40). – Pp. 25-27. – EDN JTOJBL.
18. Mylnikova, A. V. Language Models for Text Preprocessing in Machine Translation / A. V. Mylnikova, L. A. Mylnikov // Scientific and Technical Information. Series 2: Information Pro-cesses and Systems. – 2025.
19. Naumova Natalia Valerievna, Abramkov Artem Olegovich. ON THE USE OF ARTIFICIAL INTELLIGENCE IN WORKING WITH CITIZENS' APPEALS // Humanities, Social Sciences, Economics, and Law. 2022. No. 9. URL: https://cyberleninka.ru/article/n/k-voprosu-ob-ispolzovanii-iskusstvennogo-intellekta-v-sfere-raboty-s-obrashcheniyami-grazhdan (ac-cessed: 25.10.2025).
20. Ovezdurdyeva Irina Kurbangeldievna, Garadzhaeva Dzhemal Yazmyradovna. Analysis of Social Networks Using Artificial Intelligence: Modern Approaches and Prospects // Science and Worldview. 2025. No. 55. URL: https://cyberleninka.ru/article/n/analiz-sotsialnyh-setey-s-pomoschyu-iskusstvennogo-intellekta-sovremennye-podhody-i-perspektivy (accessed: 18.11.2025).
21. Saifulla S., Drezhevski R., Dwiyanto F. A., Aribowo A. S., and Fauzia Y. (2023). Analysis of sentiment using a feature-based machine learning approach to detect anxiety. In: Mikishka, J., de Mulatier, C., Pashy
22. Tumbinskaya M.V., Galiev R.A. Identification of Fake News Using a Web Resource Based on Neural Networks // Software Products and Systems. 2023 Vol. 36 No. 4 Pp. 590–599. DOI: 10.15827/0236-235X.142.590-599
23. Ulizko Maxim Valerievich, Vatyan Alexandra Sergeevna, Gusarova Natalia Fedorovna, Dobrenko Natalia Viktorovna. The use of large language models for legal expertise // EPI. 2025. No. 1. URL: https://cyberleninka.ru/article/n/primenenie-bolshih-yazykovyh-modeley-dlya-yuridicheskih-ekspertiz (date of access: 18.10.2025).
24. Yarushkina, N. G. Application of the word2vec and bert language models in the task of sentiment analysis of text messages on social networks / N. G. Yarushkina, V. S. Moshkin, A. A. Konstantinov // Automation of management processes. – 2020. – No. 3(61). – Pp. 60-69. – DOI 10.35752/1991-2927-2020-3-61-60-69. – EDN GHTFEZ.
Review
For citations:
Vanchikova E.N., Timofeev A.N., Saduev N.B., Vanzatova E.O. Development of a mathematical model for the processes of researching citizen appeals. The Herald of the Siberian State University of Telecommunications and Information Science. 2026;20(1):39-56. (In Russ.) https://doi.org/10.55648/1998-6920-2026-20-1-39-56
Views:
142
JATS XML
Email this article 
