ALGORITHM FOR COMPREHENSIVE ASSESSMENT OF THE PSYCHOEMOTIONAL STATE OF A SOCIAL NETWORK USER BASED ON ANALYSIS OF ITS MEDIA CONTENT

Abstract

Background. The rapid development of computer communications over the past 15 years has led to the emergence of virtually new forms of interpersonal and public communication, often replacing real communication – social networks and instant messengers. Such means of communication, unlike traditional forms of communication, based on the transmission of media content and, on the one hand, have an effect that encourages communication and eliminates barriers caused by psycho-emotional patterns. And on the other hand, they are an active environment for the emergence of a new form of crime – cyber fraud and cybercrime, the annual damage from which in Russia amounts to tens of billions of rubles. According to the authors, definition psycho-emotional patterns to identify such offenses is an urgent problem. The purpose of this study is to create an algorithm for a comprehensive assessment of psycho-emotional states and identify the threshold values of these states in social network users based on analysis of media content. Materials and methods. The article discusses the FER 2013 and text2emotion libraries, which used as part of recognition systems for analyzing media content. Results and conclusions. An algorithm developed for a comprehensive assessment of the psycho-emotional state of a social network user based on an analysis of his social network page. In this case, a psycho-emotional diagram constructed indicating the manifestations of extreme psychological states of the user. The presence of an algorithm for a comprehensive assessment of the psycho-emotional state of a social network user will increase the reliability of determining psycho-emotional patterns for identifying cyber fraud and cybercrime.

Keywords

• media content
• emotions
• segmentation of emotions
• algorithm for assessing psycho-emotional state
• neural networks