БАЄСІВСЬКО-ФОРСАЙТНИЙ ПІДХІД ДО ПЕРЕДБАЧЕННЯ СОЦІАЛЬНОЇ НАПРУЖЕНОСТІ В УКРАЇНІ НА СЕРЕДНЬОСТРОКОВУ ПЕРСПЕКТИВУ

M. ZGUROVSKY; M. SLIUSAREVSKY

doi:10.15407/scine22.01.051

Authors

M. ZGUROVSKY Educational and Scientifi c Complex “Institute for Applied System Analysis” of the Ministry of Education and Science of Ukraine and the National Academy of Sciences of Ukraine https://orcid.org/0000-0001-5896-7466
M. SLIUSAREVSKY Institute of Social and Political Psychology of National Academy of Educational Sciences of Ukraine https://orcid.org/0000-0002-4038-5668

DOI:

https://doi.org/10.15407/scine22.01.051

Keywords:

social tension; Bayesian model; foresight analysis; scenario planning; OSINT analytics; artificial intelligence; strategic monitoring

Abstract

Introduction. During the period of war and profound social transformations, Ukrainian society de monstrates high variability in socio-psychological reactions, which underscores the need for quantitative measurement of social tension as an indicator of societal equilibrium.
Problem Statement. Under conditions of rapid change, traditional sociological methods do not ensure timely forecasting of crisis processes because they fail to capture the nonlinearity of social dynamics and the impact of emotional and informational factors. This has created an urgent need for a cognitiveanalytical model capable of integrating large datasets, expert assessments, and Bayesian forecasting methods in real time.
Purpose. To develop an interdisciplinary approach for forecasting social tension in Ukraine for the medium term (2026—2027) using Bayesian modelling, foresight scenario analysis, OSINT monitoring, and artificial intelligence tools.
Materials and Methods. The N—CH psychosocial model has been applied to integrate cognitive, motivational, and external-evaluative parameters of public perception. Empirical data have been obtained through OSINT monitoring using the GDELT, Google Trends, and Media Cloud platforms, complemented by cognitive text analysis performed with large language models (LLaMA 3).
Results. A digital analytical platform, N—CH, has been developed to calculate the social tension indicator in real time, conduct sentiment and emotional analysis of public communications, and generate time series of societal moods. The model has revealed a cyclic dynamic of social tension in Ukraine over 2000—2025, with a peak value of CH ≈ 9 in 2022 and a trend toward stabilization at an elevated level in 2025—2027. Foresight scenario analysis has identified three baseline development trajectories — controlled peace, prolonged stagnation, and escalation and disruption — with their probabilities estimated through a Bayesian posterior distribution.
Conclusions. The proposed approach has proven effective for the quantitative forecasting of social risks and can
serve as a foundation for a strategic humanitarian security monitoring system. The N—CH model enables the early
detection of phases of social instability and improves the adaptability of government policy in the sphere of societal
resilience.

Downloads

Download data is not yet available.

References

Slyusarevskyy, M. M. (2002). Social tension: A theoretical model of necessary and sufficient indicators. Scientific Studies in Social and Political Psychology, 5(8), 24—34. URL: https://ispp.org.ua/wp-content/uploads/ 2020/05/studios-5.pdf (Last accessed: 20.10.2025).

Kredentser, O. V., Lahodzinska, V. I., Kovalchuk, O. S. (2016). Theoretical analysis of the concept of “social tension”: An interdisciplinary approach. Current Problems of Psychology, 45, 48—55. URL: https://lib.iitta.gov.ua/ id/eprint/705927 (Last accessed: 20.10.2025).

Dynamics of social moods of the population of Ukraine (2000—2023). URL: https://www.kiis.com.ua (Last accessed: 20.10.2025).

Slyusarevskyy, M. M. (2007). Diagnosis, forecasting, and correction of social tension: A conceptual model. Scientific Studies in Social and Political Psychology, 18(21), 49—69.

What is the OSINT Framework? How can you use it. URL: https://www.recordedfuture.com/threat-intelligence101/intelligence-sources-collection/osint-framework (Last accessed: 20.10.2025).

Office of the Director of National Intelligence. The IC OSINT Strategy 2024—2026. URL: https://www.dni.gov/ files/ODNI/documents/IC_OSINT_Strategy.pdf (Last accessed: 20.10.2025).

GDELT Project. (2023). Global Database of Events, Language and Tone (GDELT 2.1). URL: https://www. gdeltproject.org (Last accessed: 20.10.2025).

Google Trends. (2024). Ukraine protest dynamics 2004—2024. URL: https://trends.google.com (Last accessed: 20.10.2025).

Media Cloud Consortium. (2024). Media Cloud: Open-source media analysis platform. URL: https://mediacloud. org (Last accessed: 20.10.2025).

Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., …, Ma, Zh. (2024). The Llama 3 herd of models. arXiv Preprint. https://doi.org/10.48550/arXiv.2407.21783

Zgurovsky, M., Sineglazov, V., Chumachenko, E. (2021). Artificial Intelligence Systems Based on Hybrid Neural Networks: Theory and Applications. Cham: Springer Nature. https://doi.org/10.1007/978-3-030-85317-7

Zgurovsky, M. Z., Zaychenko, Y. P. (2019). Big Data: Conceptual Analysis and Applications. Cham: Springer. https://doi.org/10.1007/978-3-030-04352-3

Roponen, J., Salo, A. (2023). A probabilistic cross-impact methodology for explorative scenario analysis. Futures & Foresight Science, 5, e165. https://doi.org/10.1002/ffo2.165

Zgurovsky, M. Z. (2024). Foresight: Scenarios of the Russian–Ukrainian war in the context of the new Euro-Atlantic security architecture. Kyiv. URL: http://wdc.org.ua/sites/default/files/FORESIGHT2024_Euro-Atlantic_ Security_Scenarios.pdf (Last accessed: 20.10.2025).

Zgurovsky, M. Z. (2021). Foresight of the development of the defense-industrial complex of Ukraine for the period 2021—2030. Kyiv. URL: http://wdc.org.ua/sites/default/files/KPI-WDC-IADT_FORESIGHT-2021-UA.pdf (Last accessed: 20.10.2025).

Bishop, C. M. (2006). Pattern Recognition and Machine Learning. New York: Springer. https://doi.org/10.1007/ 978-0-387-45528-0

Murphy, K. P. (2022). Probabilistic Machine Learning: An Introduction. Cambridge: MIT Press. https://doi. org/10.7551/mitpress/12412.001.0001

Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., Rubin, D. B. (2013). Bayesian Data Analysis (3rd ed.). Boca Raton: Chapman & Hall/CRC. https://doi.org/10.1201/b16018

Jaynes, E. T. (2003). Probability Theory: The Logic of Science. Cambridge. https://doi.org/10.1017/CBO9780511790423

Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. Cambridge. https://doi.org/10.7551/mitpress/8179.001.0001

Morgan, M. G., Henrion, M. (1990). Uncertainty: A Guide to Dealing with Uncertainty in Quantitative Risk and Policy Analysis. Cambridge. https://doi.org/10.1017/CBO9780511809477

Cooke, R. M. (2022). Technical details of the Classical Model. Delft University of Technology. URL: https:// rogermcooke.net (Last accessed: 20.10.2025).

Scheffer, M., Bascompte, J., Brock, W. A., Brovkin, V., Carpenter, S. R., Dakos, V., Held, H., …, Sugihara, G. (2009). Early-warning signals for critical transitions. Nature, 461(7260), 53—59. https://doi.org/10.1038/nature08227

Ramakrishnan, N., Butler, P., Muthiah, S., Self, N., Khandpur, R., Saraf, P., Wang, W., …, Mares, D. (2014). “Beating the news” with EMBERS: Forecasting civil unrest using open-source indicators. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1799—1808. https://doi.org/10.1145/2623330.2623373

Inter-Agency Standing Committee. (2007). IASC Guidelines on Mental Health and Psychosocial Support in Emergency Settings. Geneva: IASC. URL: https://hr.un.org/sites/hr.un.org/files/Guidelines%20IASC%20Mental% 20Health%20Psychosocial_0.pdf (Last accessed: 20.10.2025).

World Health Organization. (2020). Risk Communication and Community Engagement (RCCE) Action Plan Guidance: COVID-19 Preparedness and Response. Geneva: WHO. URL: https://www.who.int/publications/i/ item/risk-communication-and-community-engagement-(rcce)-action-plan-guidance (Last accessed: 20.10.2025)