Towards Forecastingting the Probability of Unarmed Revolutionary Destabilization Using Machine Learning Methods

The authors provide a broad overview of the main applications for machine learning methods in political sociology. They describe history of the transition from simple regression models to complex machine learning models. The reasons for and benefits of this transition are discussed. The authors identify the main uses of machine learning models in related disciplines and describe how they have been applied to the task of predicting revolutionary episodes. A cohort of other researchers who have tackled the issue of predicting political instability in their own ways, from using multiple regression models to using machine learning as a classifier for tweets during the Arab Spring, is reviewed. An extended description of the main trends in the field of studying predictor behavior in machine learning models is given. Cases of their application and the limitations researchers may face are discussed. The authors describe different statistical approaches to the task of estimating parameters of machine learning models. Using the example of analyzing models built to predict the probability of revolutionary episodes, they discuss ways of ranking model parameters through the estimation of decision trees and changes in the resulting power of models. The authors show how correlated variables can influence the obtained ranking result, why variables can appear in different parts of the ranking under different systems of calculating their importance. The authors also consider the method of determining the boundary after which the model parameters can be considered statistically significant. The authors provide a method of generalized representation of the direction of association of different variables, taking into account their interaction with other predictors, and give an interpretation of the results obtained using Shepley vectors. Among the substantive results of the tests, it is especially worth noting the identification of an exceptionally powerful effect of revolutionary waves in revolutionary events of the 21st century, given that in the 21st century the effect of global revolutionary waves turns out to be stronger than the effect of regional waves. In general, the tests suggest that the following are particularly strong factors that significantly increase the probability of the onset of unarmed revolutionary uprisings in the 21st century (in addition to the effect of revolutionary waves): a high level of political corruption, the effect of inertia (unarmed revolutionary or powerful protest events in the recent past), anomalies in economic growth, high amounts of aid from the United States (the effect of the “iron cage of liberalism” according to Daniel Ritter), the absence of oil rent, high population, high food inflation, middle-income economy, long incumbent duration and an intermediate type of political regime.

1. Alekseev T. D. (2016). Sequence analysis in sociology: possibilities, limitations and application potential. Sociology: methodology, methods, mathematical modeling, 43, pp. 100–127. (in Russ.)

2. Borovsky A. A. (2015) Prospects for the application of machine learning technologies to the processing of large arrays of historical data. Cybernetics and programming (1), pp. 77–114. https://doi.org/10.7256/2306-4196.2015.1.13730 (in Russ.)

3. Goldstone J. A., Grinin L., Korotayev A. (2022) Waves of revolutions in the 21st century. Polis. Political Studies, (4), pp. 108–119. https://doi.org/10.17976/jpps/2022.04.09 (in Russ.)

4. Zhdanov A. I., Korotayev A. V. (2024) Inflationary Pressure and Revolutionary Destabilization: Impact Assessment and Comparative Analysis. Sociology of Power, 36 (2), pp. 113–141. https://doi.org/10.22394/2074-0492-2024-2-113-141 (in Russ.)

5. Korotayev A., Vaskin I., Bilyuga S. (2017) Olson-Huntington Hypothesis on a Bell-Shaped Relationship Between the Level of Economic Development and Sociopolitical Destabilization: A Quantitative Analysis. Russian Sociological Review, 16(1), pp. 9–49. https://doi.org/10.17323/1728-192X2017-1-9-49. (in Russ.)

6. Korotayev A., Grinin L., Ustyuzhanin V. (2024) Database of revolutionary events of the 21st century. Moscow: HSE University, 2024.

7. Korotayev A., Grinin L., Ustyuzhanin V., Fain E. (2025) The Fifth Generation of Revolution Studies. A Systematic Review. Logos, 35(1), pp. 191–316. https://doi.org/10.17323/0869-5377-2025-1-193-296. (in Russ.)

8. Korotayev A. V., Zhdanov A. I. (2023a) Quantitative analysis of political factors of revolutionary destabilization. A systematic review. Politeia-Journal of Political Theory, Political Philosophy and Sociology of Politics, 108(1), pp. 64–87. https://doi.org/10.30570/2078-5089-2023-110-3-149-171. (in Russ.)

9. Korotayev A. V., Zhdanov A. I. (2023b) A Quantitative Analysis of Economic Factors of Revolutionary Destabilization: Results and Prospects. Sociology of Power, 35(1), pp. 118-159. https://doi.org/10.22394/2074-0492-2023-1-118-159. (in Russ.)

10. Korotayev A., Isaev L., Vasilev A. (2015) Quantitative Analysis of 2013-2014 Revolutionary Wave. Sociological Studies, (8), pp. 119–127. (in Russ.)

11. Korotayev A., Sawyer P., Grinin L., Romanov D., Shishkina A. (2020) Socioeconomic development and anti-government protests in light of a new quantitative analysis of global databases. Sociological Journal, 26(4), pp. 61–78. https://doi.org/10.19181/socjour.2020.26.4.7642. (in Russ.)

12. Korotayev A. V., Shishkina A. R., Isaev L. M. (2016) The Arab Spring as a trigger of the global phase transition. Polis. Political Studies, (3), pp. 108–122. https://doi.org/10.17976/jpps/2016.03.09 (in Russ.)

13. Medvedev I. A., Korotayev A. V. (2020) Towards the construction of an index of socio-political destabilization in various world-system zones. Systematic monitoring of global and regional risks, 11, pp. 433–454. (in Russ.)

14. Musieva J. M., Ustyuzhanin V. V., Grinin L. E., Korotayev A. V. (2023) Subjective Wellbeing and Revolutionary Destabilization. A Quantitative Analysis. Sociology of Power, 35 (3), pp. 57–94. https://doi.org/10.22394/2074-0492-2023-3-57-94. (in Russ.)

15. Ustyuzhanin V., Grinin L., Medvedev I., Korotayev A. (2022) Education and Revolutions. Why do some revolutions take up arms while others do not? PoliteiaJournal of Political Theory, Political Philosophy and Sociology of Politics, 104(1), pp. 50–71. https://doi.org/10.30570/2078-5089-2022-104-1-50-71. (in Russ.)

16. Ustyuzhanin V., Zhodzishskaya P., Korotayev A. (2022) Demographic Factors as Predictors of Revolutionary Situations: Experience in Quantitative Analysis. Sociological Journal, 28(4), pp. 34–59. https://doi.org/10.19181/socjour.2022.28.4.9314. (in Russ.)

17. Ustyuzhanin V. V., Korotayev A. V. (2022) Regression modeling of armed and unarmed revolutionary destabilization in the Afrasian macrozone of instability. Systemic Monitoring of Global and Regional Risks, 13, pp. 211–244. https://doi.org/10.30884/978-5-7057-6184-5_07. (in Russ.)

18. Ustyuzyhanin V., Kostin M., Grinin L., Korotayev A. (2023) Corruption and revolutionary destabilization: quantitative research experience. The Journal of Sociology and Social Anthropology, 26(3), pp. 53–99. https://doi.org/10.31119/jssa.2023.26.3.3. (in Russ.)

19. Ustyuzhanin V., Mikheeva V., Sumernikov E., Korotayev A. (2023) Economic Origins of Revolutions: the link between GDP and revolutionary risks. PoliteiaJournal ofPolitical Theory, Political Philosophy and Sociology ofPolitics, 108(1), pp. 64–87. https://doi.org/10.30570/2078-5089-2023-108-1-64-87. (in Russ.)

20. Ustyuzhanin V., Stepanishcheva Y., Gallyamova A., Grinin L., Korotayev A. (2023). Education and Revolutionary Destabilization Risks: A Quantitative Analysis. Russian Sociological Review, 22(1), pp. 98–128. https://doi.org/10.17323/1728-192X-2023-1-98-128. (in Russ.)

21. Ustyuzhanin V. V., Sumernikov E. A., Grinin L. E., Korotayev A. V. (2022). Urbanization and Revolutions: a Quantitative Analysis. Sociological Studies, (10), pp. 85–95. https://doi.org/10.31857/S013216250018478-8. (in Russ.)

22. Beissinger M.R. (2017) “Conventional” and “virtual” civil societies in autocratic regimes. Comparative Politics, 49(3), pp. 351–371. http://dx.doi.org/10.5129/001041517820934267

23. Beissinger M. R. (2022) The revolutionary city: Urbanization and the global transformation of rebellion. Princeton, NJ: Princeton University Press.

24. Ben Bouallègue Z. et al. (2024) The Rise of Data-Driven Weather Forecasting: A First Statistical Assessment of Machine Learning–Based Weather Forecasts in an Operational-Like Context. Bulletin of the American Meteorological Society, 105(6), pp. 864–883. https://doi.org/10.1175/BAMS-D-23-0162.1

25. Blair R. A., Sambanis N. (2020) Forecasting civil wars: Theory and structure in an age of “big data” and machine learning. Journal of Conflict Resolution, 64(10), pp. 1885–1915. https://doi.org/10.1177/0022002720918923

26. Braithwaite A., Braithwaite J. M., Kucik J. (2015) The conditioning effect of protest history on the emulation of nonviolent conflict. Journal of Peace Research, 52(6), pp. 697–711. https://doi.org/10.1177/0022343315593993.

27. Braithwaite A., Kucik J., Maves J. (2014) The costs of domestic political unrest. International Studies Quarterly, 58(3), pp. 489–500. https://doi.org/10.1111/isqu.12061.

28. Brooks R., White P. B. (2023) The military before the march: Civil-military grand bargains and the emergence of nonviolent resistance in autocracies. Journal of Peace Research, 61(6), pp. 1002–1018. https://doi.org/10.1177/00223433231180921

29. Brunnschweiler C. N., Lujala P. (2019) Economic backwardness and social tension. The Scandinavian Journal of Economics, 121(2), pp. 482–516. https://doi.org/10.1111/sjoe.12281

30. Butcher C., Svensson I. (2016) Manufacturing dissent: Modernization and the onset of major nonviolent resistance campaigns. Journal of Conflict Resolution, 60(2), pp. 311–339. https://doi.org/10.1177/0022002714541843

31. Caves R. E. (1976) Economic models of political choice: Canada’s tariff structure. Canadian Journal of Economics, 9(2), pp. 278–300. https://doi.org/10.2307/134522

32. Cebul M. D., Grewal S. (2022) Military conscription and nonviolent resistance. Comparative Political Studies, 55(13), pp. 2217–2249. https://doi.org/10.1177/00104140211066209

33. Chadefaux T. (2023) An automated pattern recognition system for conflict. Journal of Computational Science, 72, pp. 102–114. https://doi.org/10.1016/j.jocs.2023.102074

34. Chadefaux T. (2014) Early warning signals for war in the news. Journal of Peace Research, 51(1), pp. 5–18. https://doi.org/10.1177/0022343313507302

35. Chan J. Y. L. et al. (2022) Mitigating the multicollinearity problem and its machine learning approach: a review. Mathematics, 10(8), pp. 1283–1291. http://dx.doi.org/10.3390/math10081283

36. Chenoweth E., Ulfelder J. (2017) Can structural conditions explain the onset of nonviolent uprisings? Journal of Conflict Resolution, 61(2), pp. 298–324. https://doi.org/10.1177/0022002715576574

37. Dahl M., Gates S., Gleditsch K., González B. (2021) Accounting for Numbers: Group Characteristics and the Choice of Violent and Nonviolent Tactics. The Economics of Peace and Security Journal, 16(1), pp. 1–25. https://doi.org/10.15355/epsj.16.1.5

38. De Mol C., Giannone D., Reichlin L. (2008) Forecasting using a large number of predictors: Is Bayesian shrinkage a valid alternative to principal components? Journal of Econometrics, 146(2), pp. 318–328. https://doi.org/10.1016/j.jeconom.2008.08.011

39. Dorward N., Fox S. (2022) Population pressure, political institutions, and protests: A multilevel analysis of protest events in African cities. Political Geography, 99, pp. 102–111. https://doi.org/10.1016/j.polgeo.2022.102762

40. Edwards P. K. (1978) Time Series Regression Models of Strike Activity: A Reconsideration with American Data. British Journal of Industrial Relations, 16(3), pp. 47–62. https://doi.org/10.1111/j.1467-8543.1978.tb00289.x

41. Gleditsch K. S., Metternich N. W., Ruggeri A. (2014) Data and progress in peace and conflict research. Journal of Peace Research, 51(2), pp. 301–314. https://doi.org/10.1177/0022343313496803

42. Goldsmith B. E., Chalup S. K., Quinlan M. J. (2008) Regime type and international conflict: towards a general model. Journal of Peace Research, 45(6), pp. 743–763. https://doi.org/10.1177/0022343308096154

43. Goldstone J. A. et al. (2010) A global model for forecasting political instability. American journal of political science, 54(1), pp. 190–208. https://doi.org/10.1111/j.1540-5907.2009.00426.x

44. Goldstone J. A., Grinin L., Korotayev A. (2022) Introduction. Changing yet Persistent: Revolutions and Revolutionary Events. In: J. A. Goldstone, L. Grinin, A. Korotayev (Eds.), Handbook of Revolutions in the 21st Century: The New Waves of Revolutions, and the Causes and Effects of Disruptive Political Change (pp. 1–34). Cham: Springer Nature. https://doi.org/10.1007/978-3-030-86468-2_1

45. Grinin L. (2022) On revolutionary waves since the 16th century. In: J. A. Goldstone, L. Grinin, A. Korotayev (Eds.), Handbook of Revolutions in the 21st Century: The New Waves of Revolutions, and the Causes and Effects of Disruptive Political Change (pp. 389–411). Cham: Springer Nature. https://doi.org/10.1007/978-3-030-86468-2_13

46. Grinin L., Grinin A. (2022) Revolutionary Waves and Lines of the 20th Century //In: Goldstone J. A., Grinin L., Korotayev A. (Eds.), Handbook of Revolutions in the 21st Century: The New Waves of Revolutions, and the Causes and Effects of Disruptive Political Change (pp. 315-388). Cham: Springer Nature. https://doi.org/10.1007/978-3-030-86468-2_12

47. Grinin L., Grinin A. Korotayev A. (2022) 20th century revolutions: characteristics, types, and waves. Humanities and Social Sciences Communications, 9(1), pp. 1–13. https://doi.org/10.1057/s41599-022-01120-9.

48. Grinin L., Korotayev A. (2024) Is the Fifth Generation of Revolution Studies Still Coming? Critical Sociology, 50(6), pp. 1039–1067. https://doi.org/10.1177/08969205241245215

49. Grinin L., Korotayev A., Tausch A. (2019) Islamism, Arab Spring, and the Future of Democracy. World System and World Values Perspectives. Cham: Springer Nature. https://doi.org/10.1007/978-3-319-91077-2

50. Grömping U. (2015) Variable importance in regression models. Wiley interdisciplinary reviews: Computational statistics, 7(2), pp. 137-152. https://doi.org/10.1002/wics.1346

51. Hamilton R. I., Papadopoulos P. N. (2023) Using SHAP values and machine learning to understand trends in the transient stability limit. IEEE Transactions on Power Systems, 39(1), pp. 1384–1397. https://doi.org/10.1109/TPWRS.2023.3248941

52. Honaker J., King G., Blackwell M. (2011) Amelia II: A program for missing data. Journal of statistical software, 45(7), pp. 1–47. https://doi.org/10.18637/jss.v045.i07

53. Huang H., Boranbay-Akan S., Huang L. (2019). Media, protest diffusion, and authoritarian resilience. Political Science Research and Methods, 7(1), pp. 23–42. https://doi.org/10.1017/psrm.2016.25

54. Issaev L., Korotayev A. (2022) Introduction. New Wave of Revolutions in the MENA region//In: Issaev L., Korotayev A. (Eds.), New wave of revolutions in the MENA region. A comparative perspective (pp. 1–32). Cham: Springer. https://doi.org/10.1007/978-3-031-15135-4_1

55. Joseph K., Carley K. M., Filonuk D., Morgan G. P., Pfeffer J. (2014) Arab Spring: from newspaper. Social Network Analysis and Mining, 4(177), pp. 1–17. https://doi.org/10.1007/s13278-014-0177-5

56. Kavada A. (2020) Creating the collective: social media, the Occupy Movement and its constitution as a collective actor. Protesttechnologies and media revolutions (pp. 107-125). Emerald Publishing Limited.

57. Keele L. J. (2008) Semiparametric regression for the social sciences. Hoboken, NJ: John Wiley & Sons.

58. King G. (1988) Statistical models for political science event counts: Bias in conventional procedures and evidence for the exponential Poisson regression model. American Journal of Political Science, 32(3), pp. 838–863. https://doi.org/10.2307/2111248

59. Knutsen C. H. (2014) Income Growth and Revolutions. Social Science Quarterly, 95(4), pp. 920–937. https://doi.org/10.1111/ssqu.12081

60. Korotayev A., Grinin L., Ustyuzhanin V., Fain E. (2025) The Fifth Generation of Revolution Studies. Part I: When, Why and How Did It Emerge. Critical Sociology, 51(2), pp. 257–282. https://doi.org/10.1177/08969205241300596

61. Korotayev A., Issaev L., Zinkina J. (2015) Center-periphery dissonance as a possible factor of the revolutionary wave of 2013–2014: A cross-national analysis. Cross-Cultural Research, 49(5), pp. 461–488. https://doi.org/10.1177/1069397115595374

62. Korotayev A., Medvedev I., Zinkina J. (2022) Global Systems for Sociopolitical Instability Forecasting and Their Efficiency: A Comparative Analysis. Comparative Sociology, 21(1), pp. 64–104. https://doi.org/10.1163/15691330-bja10050

63. Korotayev A. V., Sawyer P. S., Romanov D. M. (2021) Socio-economic development and protests: A quantitative reanalysis. Comparative Sociology, 20(2), pp. 195–222. https://doi.org/10.1163/15691330-bja10030

64. Korotayev A., Ustyuzhanin V., Grinin L., Fain E. (2025) The fifth generation of revolution studies. Part II: A systematic review of substantive findings (Revolution Causes, Forms, and Waves). Critical Sociology 51(3), pp. 429–450. https://doi.org/10.1177/08969205241300595

65. Korotayev A., Vaskin I., Bilyuga S., Ilyin I. (2018) Economic Development and Sociopolitical Destabilization: A Re-Analysis. Cliodynamics, 9(1), pp. 59–118. https://doi.org/10.21237/c7clio9137314

66. Korotayev A., Zhdanov A., GrininL., UstyuzhaninV. (2025) Revolutionand Democracy in the Twenty-First Century. Cross-Cultural Research, 59(2), pp. 180–215. https://doi.org/10.1177/10693971241245862

67. Kostin M., Korotayev A. (2024) USAID Democracy Promotion as a Possible Predictor of Revolutionary Destabilization. Comparative Sociology, 23(2), pp. 240–278. https://doi.org/10.1163/15691330-bja10102

68. Lahiri K., Monokroussos G., Zhao Y. (2016) Forecasting consumption: The role of consumer confidence in real time with many predictors. Journal of Applied Econometrics, 31(7), pp. 1254–1275. https://doi.org/10.1002/jae.2494

69. Lall R. (2016) How multiple imputation makes a difference. Political Analysis, 24(4), pp. 414–433. https://doi.org/10.1093/pan/mpw020

70. Levin N., Ali S., Crandall D. (2018) Utilizing remote sensing and big data to quantify conflict intensity: the Arab Spring as a case study. Applied Geography, 94, pp. 1–17. https://doi.org/10.1016/j.apgeog.2018.03.001

71. Li F., Yang Y. (2003) A loss function analysis for classification methods in text categorization. Proceedings of the 20th international conference on machine learning (ICML-03), pp. 472–479.

72. Lotan G., Graeff E., Ananny M., Gaffney D., Pearce I. (2011) The Arab Spring| the revolutions were tweeted: Information flows during the 2011 Tunisian and Egyptian revolutions. International journal of communication, 5(5), pp. 1375–1405.

73. Medvedev I., Ustyuzhanin V., Zinkina J., Korotayev A. (2022) Machine learning for ranking factors of global and regional protest destabilization with a special focus on Afrasian instability macrozone. Comparative Sociology, 21 (6), pp. 604–645. https://doi.org/10.1163/15691330-bja10062

74. Muthukumar V. et al. (2021) Classification vs regression in overparameterized regimes: Does the loss function matter? Journal of Machine Learning Research, 22(222), pp. 1–69.

75. Nicodemus K. K. et al. (2010) The behaviour of random forest permutation-based variable importance measures under predictor correlation. BMC bioinformatics, 11, pp. 1–13. https://doi.org/10.1186/1471-2105-11-110

76. Nirmalraj S. et al. (2023) Permutation feature importance-based fusion techniques for diabetes prediction. Soft Computing, 2023, pp. 1–12. https://doi.org/10.1007/s00500-023-08041-y

77. Pinckney J., RezaeeDaryakenari B. (2022) When the levee breaks: A forecasting model of violent and nonviolent dissent. International Interactions, 48(5), pp. 997–1026. https://doi.org/10.1080/03050629.2022.2090933

78. Ritter D. P. (2015) The iron cage of liberalism: International politics and unarmed revolutions in the Middle East and North Africa. Oxford: Oxford University Press.

79. Rozov N. (2022) Typology and principles of dynamics of revolutionary waves in world history. In: J. A. Goldstone, L. Grinin, A. Korotayev (Eds.), Handbook of Revolutions in the 21st Century: The New Waves of Revolutions, and the Causes and Effects of Disruptive Political Change (pp. 241–264). Springer. https://doi.org/10.1007/978-3-030-86468-2_9

80. Sun X. et al. (2012) Using cooperative game theory to optimize the feature selection problem. Neurocomputing, 97, pp. 86–93. https://doi.org/10.1016/j.neucom.2012.05.001

81. Tang J., Liu H. (2012) Feature selection with linked data in social media. Proceedings of the 2012 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, pp. 118–128.

82. Taylor L., Schroeder R., Meyer E. (2014) Emerging practices and perspectives on Big Data analysis in economics: Bigger and better or more of the same? Big Data & Society, 1(2), article 2053951714536877. https://doi.org/10.1177/2053951714536877

83. Tremayne M. (2016) Anatomy of protest in the digital era: A network analysis of Twitter and Occupy Wall Street. Social Networks and Social Movements. London: Routledge, pp. 110–126.

84. Tumasjan A. et al. (2010) Predicting elections with twitter: What 140 characters reveal about political sentiment. Proceedings of the international AAAI conference on web and social media, 4(1), pp. 178–185. https://doi.org/10.1609/icwsm.v4i1.14009

85. Ulfelder J. (2012) Forecasting Political Instability: Results from a Tournament of Methods. Available at SSRN 2156234.

86. Ustyuzhanin V., Korotayev A. (2023) Revolutions and Democracy. Can Democracies Prevent Revolutionary Armed Violence? Comparative Sociology, 22(1), pp. 95–137. https://doi.org/10.1163/15691330-bja10073

87. Ustyuzhanin V. V., Sawyer P. S., Korotayev A. V. (2023) Students and protests: A quantitative cross-national analysis. International Journal of Comparative Sociology, 64(4), pp. 375–401. https://doi.org/10.1177/00207152221136042

88. Von Eschenbach W. J. (2021) Transparency and the black box problem: Why we do not trust AI. Philosophy & Technology, 34(4), pp. 1607–1622. https://doi.org/10.1007/s13347-021-00477-0

89. Yun Y. H., Liang F., Deng B. C., Lai G. B., Vicente Gonçalves C. M., Lu H. M., Liang Y. Z. (2015) Informative metabolites identification by variable importance analysis based on random variable combination. Metabolomics, 11, pp. 1539–1551. https://doi.org/10.1007/s11306-015-0803-x