UDC 517
ANALYSIS OF SOCIODYNAMIC PROCESSES TIME SERIES CHARACTERISTICS IN COMMENT NETWORKS OF MASS MEDIA USERS
K. K. Otradnov, lecturer, the Department of Information Warfare of the Institute of Cybersecurity and Digital Technolo-gies, MIREA – Russian Technological University, Moscow, Russia;
orcid.org/0000-0002-0055-9651 e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
J. P. Perova, lecturer, the Chair of Telecommunications, Institute of Radio Electronics and Computer Science, MIREA – Russian Technological University, Moscow, Russia;
orcid.org/0000-0003-4028-2842 e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
V. R. Grigoriev, Ph.D. (Tech.), Associate Professor, Head of the Department of Information Warfare, Institute of Cybersecurity and Digi-tal Technologies MIREA – Russian Technological University, Moscow, Russia;
orcid.org/0000-0003-0279-6391 e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
D. O. Zhukov, Dr. Sc. (Tech.), full professor, Professor of the Department of Information Warfare of the Institute of Cybersecurity and Digital Technologies, MIREA – Russian Technological UniversityMoscow, Russia;
orcid.org/0000-0002-1211-5214 e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The article analyzes the dynamics and characteristics of sociodynamic processes time series in comment networks of mass media users. There is a small amount of asymmetry in the distribution of amplitudes of changes in user activity when commenting on news and the distribution of amplitudes is almost symmetrical, but there is a so–called «heavy tail» – distribution density graphs lie above the normal distribution graph. The studies conducted allow us to draw a number of important conclusions that the time series studied are non-stationary, and the processes and systems described by them have short-term memory (the Hurst index is significantly less than 0.5). A significant difference between the Hurst indicators defined for them from 0.5 indicates that the processes or systems described by them not only have memory, but also that their structure has a fractal character. Fractality may be related to the fact that the observed processes are characterized by fractional measurement variables, which means that it is advisable to use fractional differential equations in the derivation of approximating density functions of their parameters distribution in order to build predictive models.
Key words: sociodynamic processes, activity of users of network mass media, time series, Hurst index, memory, self-similarity, fractality of time series.