Laboratory workshop on "Structural factors of peaceful and armed revolutionary change of power: experience of analysis by machine learning methods"

On April 23, the regular seminar of the laboratory was held. The report was made by Ilya A. Medvedev.

The experience of analyzing many revolutionary episodes shows that most cases of power change are influenced by a significant number of structural factors - demographic, political, social, economic, and so on. The report talks about our attempts to systematically analyze the achievements of various authors in the field of studying revolutions and protest movements. For this, a machine learning approach is used, with the help of which it is possible, within the framework of one statistical model, to analyze the influence of many factors on the occurrence of instability, as well as to rank the results obtained according to the level of their influence. We analyze various types of machine learning models, as well as several approaches to analyzing the results obtained.