Construction of an Intelligent Evaluation Model of Mental Health Based on Big Data

Abstract

In this paper, mental health data were used to evaluate the educational effects, in which the high and low scorers of three emotions, autism, positivity, and anxiety, are compared separately to explore the subtle differences in the long-term trends of the sensing traits of people with opposite characteristics. Based on the fusion of multiple kinds of sensing traits, the differences in physical and mental health assessment of positive and negative emotions by different fusion trait approaches are explored, and speech and behavioural traits are fused to build a physical and mental health assessment system for positive and negative emotions. Energy gravity uses physical distance to estimate the residual energy of nodes and considers the energy distribution of downstream nodes. The main work is to combine the data of mental health of higher education students using data mining techniques, to analyze the feasibility study of mental health education of college students. Relevant definitions, classifications, tasks, processes, and application areas of data mining techniques are introduced, and the basic principles of data mining are analyzed in detail. Taking the mental health assessment data of new students as the research object, the decision tree algorithm is used to construct a decision tree model for students with depressive symptoms, and an association rule algorithm is used to data mine the relationship between factors of psychological dimensions. Finally, it can find out the hidden laws and knowledge behind the data information and analyze the relationship that exists between psychological problems and students.