Analysis and Prediction of College Students' Mental Health Based on K-means Clustering Algorithm

Abstract

Mental health is an important basic condition for the adult development of college students, and education workers gradually pay attention to the strengthening of mental health education for college students. In this paper, a psychological management system based on the K-means clustering analysis method is proposed. Based on the basic functions of the traditional system, the students' psychological data are reutilised by using the idea of data mining. By optimising the iterative process of the K-means algorithm, the valuable parts of a large number of precipitation students' psychological data are extracted. A data model is established and it provides decision guidance for managers to scientifically manage students' mental health process. The system establishes the data mining model in the process of analysis, carries on the mining to the students' psychological data in the database, analyses the different college students' mental health state characteristics and provides the corresponding solution. The part of the test drew on mental health data from 1,000 students at a school, and the results show that the system uses the k-means algorithm to divide students into 3 categories, which are 20.6%, 31.9% and 47.1% respectively, which are 1.6% different from the data test results in the ideal state.