Abstract:
The negative psychological consequences of the COVID-19 pandemic and the forced isolation of a large proportion of people worldwide have demonstrated the need to develop ways and technologies to reduce the effects of sudden threats of this type. The basis of any practical work to minimize the negative psychological consequences of the COVID-19 pandemic associated with substance use is the monitoring and diagnosis of the psychological resources of the individual. The article aims to show the possibilities of predicting the behavior of an individual through the content analysis of posts and reposts of their profile on the social network VKontakte on the example of the propensity to use psychoactive substances and to substantiate the possibilities of optimizing and automating such prediction through the use of category markers. Content analysis was carried out by latent semantic analysis of texts extracted from posts and reposts of VKontakte social network users with subsequent content analysis through selecting markers - category words. As a result, a categorical grid was built, which increases the efficiency of content analysis of posts and reposts of users and is suitable for further automation of such research by machine learning methods.
