Automated Destructive Behavior State Detection on the 1D CNN-Based Voice Analysis

The article considers one of the approaches to the solution of the problem of finding the effect of a user on the Internet through media files including acoustic materials. The solution to the given problem is a part of the project on the development of a uniform socio-cyberphysical control system of the Internet content to identify the destructive materials and protect Internet users. Authors developed an algorithm including a classification model based on an artificial neural network (1D CNN-based) with the application of deep learning and the further application of the statistical probability approach to the solution of the problem of identification of the destructive type of emotion with the accuracy of 74%. The article considers one of the approaches to solving the problem of identifying the impact on the Internet of a user through media files, including acoustic materials. The solution to this problem is an integral part of the project to create a unified socio-cyberphysical system for managing Internet content in order to identify destructive materials and protect network users.