C&SA | Contents

Volume 62 >>> № 3 MAY — JUNE 2026

-->

UDC 004.8:007:005.52:316.4

M.Z. Zgurovsky
Educational and Research Complex "Institute for Applied Systems Analysis" of the Ministry of Education and Science of Ukraine and the National Academy of Sciences of Ukraine, Kyiv, Ukraine, zgurovsm@hotmail.com

A SYSTEM DYNAMICS AND PROBABILISTIC APPROACH TO EARLY WARNING
OF COMPLEX SOCIAL CRISES

Abstract. This paper demonstrates that contemporary complex social crises exhibit a nonlinear, multifactorial nature and emerge from the interaction of social tension, economic, security, and information factors, with social resilience acting as a constraining (damping) mechanism. The proposed methodology is based on the construction of an integral crisis pressure index C (t ) using open-source information analysis and cognitive analytics of large-scale textual data, system dynamics modeling (SDM), and its subsequent probabilistic interpretation within a dynamic Bayesian network (DBN) framework to generate multi-level early warning signals (EWS) of complex social crises. The approach is validated using empirical data from Ukraine for the period 2022–2025, which enables the identification of latent escalation phases and a quantitative assessment of the role of social resilience in mitigating crisis dynamics. The obtained results demonstrate the feasibility of transitioning from reactive monitoring to preventive, risk-informed management of social resilience under conditions of complex social crises.

Keywords: complex social crises, system dynamics, dynamic Bayesian networks, early warning, cognitive analytics, social resilience.

full text

REFERENCES

1. Global risks report 2024. World Economic Forum. 2024. URL: https://www.weforum.org/reports/global-risks-report-2024.
2. Global economic prospects. World Bank Group. 2023. URL: https://www.worldbank.org/en/publication/global-economic-prospects.
3. Our common agenda. United Nations. 2021. URL: https://www.un.org/en/common-agenda.
4. Bollen J., Mao H., Zeng X. Twitter mood predicts the stock market. Journal of Computational Science. 2011. Vol. 2, Iss. 1. P. 1–8. https://doi.org/10.1016/j.jocs.2010.12.007.
5. Li X., Patterson E., Mabry P.L., Osgood N.D. Compositional system dynamics: The higher mathematics underlying system dynamics diagrams & practice. arXiv:2509.18475v1 22 Sep 2025. https://doi.org/10.48550/arXiv.2509.18475.
6. Conflict and Fragility. OECD. 2025. URL: https://www.oecd.org/dac/conflict-fragility-resilience/global-trends-in-fragility/.
7. Human impact assessment: Ukraine. United Nations Development Programme. 2023. 128 p. URL: https://www.undp.org/sites/g/files/zskgke326/files/2023-09/undp-ua-hia-3.pdf.
8. Early warning systems and early action in fragile, conflict-affected and violent contexts: Addressing growing climate and disaster risks. United Nations Office for Disaster Risk Reduction (UNDRR). Centre of Excellence for Climate and Disaster Resilience. 2025. URL: https://www.undrr.org/publication/documents-and-publications/early-warning-systems-and-early-action-fragile-conflict.
9. What are early warning systems and why do they matter for climate action. UNDP Climate Promise. 2025. URL: https://climatepromise.undp.org/news-and-stories/what-are-early-warning-systems-and-why-do-they-matter-climate-action.
10. The IC OSINT strategy 2024–2026. Office of the Director of National Intelligence. 2024. 12 p. URL: https://www.dni.gov/files/ODNI/documents/IC_OSINT_Strategy.pdf.
11. GDELT Project. Watching our world unfold. 2023. URL: https://www.gdeltproject.org.
12. Google Trends. Ukraine protest dynamics 2004–2024. Google LLC. 2024. URL: https://trends.google.com.
13. Media Cloud, an open-source platform for media analysis. Media Cloud Project. 2024. URL: https://mediacloud.org.
14. Strategic foresight report 2023. Luxembourg: Publications Office of the European Union, 2023. 36 p. URL: https://commission.europa.eu/system/files/2023-07/SFR-23-beautified-version_en_0.pdf.
15. Strategic foresight toolkit for resilient public policy. Report. Paris: OECD Publishing, 2025. 174 p. URL: https://www.oecd.org/content/dam/oecd/en/publications/reports/2025/01/foresight-toolkit-for-resilient-public-policy_9ad1cd60/bcdd9304-en.pdf.
16. The Llama 3 Herd of Models. arXiv:2407.21783v3 [cs.AI] 23 Nov 2024. https://doi.org/10.48550/arXiv.2407.21783.
17. Kungurtsev V., Idlahcen F., Rysavy P., Rytir P., Wodecki A. Learning dynamic Bayesian networks from data: Foundations, first principles and numerical comparisons. arXiv:2406.17585v2 [cs.LG] 30 Aug 2024. https://doi.org/10.48550/arXiv.2406.17585.
18. Maasch J., Neiswanger W., Ermon S., Kuleshov V. Probabilistic graphical models: A concise tutorial. arXiv:2507.17116v1 [cs.LG] 23 Jul 2025. https://doi.org/10.48550/arXiv.2507.17116.
19. Crisis group’s impact highlights: March to October 2023. International Crisis Group. 2023. URL: https://www.crisisgroup.org/global/crisis-groups-impact-highlights-march-october-2023.
20. Zgurovsky M.Z., Sliusarevsky M.M. Bayesian-foresight approach to the prediction of social tension in Ukraine in the medium term. Science and Innovation. 2026. Vol. 22, N 1. Р. 51–68. https://doi.org/10.15407/scine22.01.051.
21. Nardo M., Saisana M., Saltelli A., Tarantola S. Tools for composite indicators building. EUR 21682 EN. 2005. JRC31473. 2005. URL: https://publications.jrc.ec.europa.eu/repository/handle/JRC31473.
22. Sterman J.D. Business DYNAMICS: Systems thinking and modeling for a complex world. McGraw-Hill School Education Group, 2000. 768 p. URL: https://books.google.com.ua/books/about/Business_Dynamics.html?id=WQZrLgEACAAJ.
23. Hyndman R.J., Athanasopoulos G. Forecasting: Principles and practice. 3rd ed. Melbourne: OTexts, 2021. 442 p. URL: https://otexts.com/fpp3/.
24. Murphy K.P. Dynamic Bayesian networks: Representation, inference and learning. Berkeley: University of California, 2002. 536 p. URL: https://books.google.com.ua/books/about/Dynamic_Bayesian_Networks.html?id=4Uc6HQAACAAJ.
25. Pearl J. Causality: Models, reasoning, and inference. 2nd ed. Cambridge University Press, 2009. 484 p. URL: https://books.google.com/books/about/Causality.html?id=f4nuexsNVZIC.
26. Helbing D., Frey B.S., Gigerenzer G., et al. Will democracy survive big data and artificial intelligence? Scientific American, 2017. URL: https://www.scientificamerican.com/article/will-democracy-survive-big-data-and-artificial-intelligence/.
27. Helbing D. Globally networked risks and how to respond. Nature. 2013. Vol. 497, N 7447. P. 51–59. https://doi.org/10.1038/nature12047.
28. Murphy K.P. Probabilistic machine learning: Advanced topics. Cambridge: MIT Press, 2023. 1360 p. URL: https://probml.github.io/pml-book/book2.html.
29. Risk and regulatory policy: Improving the governance of risk. Paris: OECD Publishing, 2010. 248 p. https://doi.org/10.1787/9789264082939-en.
30. Linkov I., Trump B.D. The science and practice of resilience. Cham: Springer, 2019. XIV, 209 p. https://doi.org/10.1007/978-3-030-04565-4.

UDC 004.8:007:005.52:316.4

A SYSTEM DYNAMICS AND PROBABILISTIC APPROACH TO EARLY WARNING OF COMPLEX SOCIAL CRISES

REFERENCES

A SYSTEM DYNAMICS AND PROBABILISTIC APPROACH TO EARLY WARNING
OF COMPLEX SOCIAL CRISES