TECHNOLOGY FOR SELECTING MUSICAL GENRES TAKING INTO ACCOUNT HUMAN MENTAL HEALTH BASED ON MACHINE LEARNING

Abstract

The research considers the technology of intelligent selection of musical genres taking into account human mental health based on machine learning methods. The relevance of using music therapy as an effective non-drug approach to improving emotional state, reducing stress, anxiety and preventing psychoemotional disorders is substantiated. Modern scientific research on the influence of music on mental health is analyzed, as well as existing approaches to recommender systems in the field of healthcare. A comparative analysis of the performance of various machine learning methods for the task of classifying and predicting the user’s psychoemotional state is conducted, based on the results of which the most relevant algorithm is selected. Hyperparameters are selected and optimized in order to increase the accuracy, stability and generalization ability of the model. A concept of a system that provides personalized selection of musical genres according to the individual psychological characteristics of the user is proposed. The compliance of the developed technology with the principles of explanatory and responsible artificial intelligence is outlined, in particular with regard to the transparency of decisions, the ethics of data use and the minimization of potential risks. The consistency of the research results with the UN Sustainable Development Goals is shown, in particular in the context of ensuring well-being, mental health and access to innovative digital technologies in the field of healthcare.