Project “Development of an Algorithm of Identification of Risk Factors for Social Media User Safety Based on Content Analysis and Psychological Characteristics of Content Consumers” RNF No. 19-78-10122

Project Manager – Valeria Vladimirovna Matsuta.

Project executor from the Institute of Distance Education – Artyom Viktorovich Feshchenko.

The project is aimed at development of a model of identification and forecasting of safety risk factors in social media, based on the analysis of social media content, digital footprints, behavioral and psychological user data.

The project is relevant because of increasing gap between the level of involvement of children and teenagers in social media, and the understanding of the mechanism of online information consumption and the impact of unsafe content on children and teenagers, who form 90% of social media users.

Despite the current policy of counteraction to and blocking of the restricted content in social media, the quantity of communities and user accounts spreading unsafe content is constantly growing.

As the most important socialization institute, social media makes children and teenagers specifically vulnerable for destructive impact due to immature mechanisms of resistance of negative information and passive, non-critical information consumption.

The academic novelty of this project consists in development of a complex model of social media safety risk factors based on the algorithm of identification of unsafe content in social media in connection with psychological characteristics of its consumers.

As part of this project, based on a sample of up to 10,000 users, for the first time in Russia, methods and tools will be created to define and classify:

  • forms of unsafe content in social media in the Russian Internet segment;
  • communities, user accounts producing and spreading unsafe content;
  • psychological, individual topological and pathological and characterological features of users of unsafe content of social media among children, teenagers and young adults (in connection with patterns of producing and consuming the content of social media);
  • risk groups of users vulnerable to unsafe content.

The following will be developed for the first time:

  • algorithm of identification of users from the high-risk group on consumption and spread of unsafe content, using the methods of machine learning and analysis of big open user data from social media;
  • social media monitoring tool based on digital footprints, behavioral and psychological user data with determination of the main safety risk factors and identification of users entering the high-risk groups;
  • web application for self-diagnostics of safety risks in social media;
  • recommendations for working with high-risk groups among children, teenagers, and young adults based on the relevant data on information trends in social media.