Intelligent system for text-based diagnostics of deviant states of individual

The article is devoted to the development of the concept of an intelligent system for diagnosing deviant states of individuals based on text analysis using mainly the following text analysis tools: convolutional neural networks, algorithms used by psychiatrists in detecting deviant states of individuals (such as extremism, suicidality, etc.), as well as the theory of information images/representations. Such a system makes it possible to significantly increase the efficiency of identifying such conditions as compared to classical monitoring methods based on content analysis.