Data mining technology in the analysis of college students’ psychological problems

Abstract

This paper expounds on the research status of data mining and the status quo of college students? psychological health problems, deeply analyzing the feasibility of introducing data mining technology into the analysis of college students? psychological health. After studying and analyzing the decision tree technology of data mining, and taking the psychological health problem data of the students in a university in 2021 as the research object, this paper uses the decision tree to analyze the psychological health problem data. The main work includes the following: determining the mining object and mining target; preprocessing the original data; and according to the characteristics of the data used, choosing the C4.5 algorithm of the decision tree to construct the decision tree of the students. Finally, based on the analysis and comparison of the decision tree model before and after pruning, classification rules are extracted from the optimal decision tree model, thus providing a scientific decision-making basis for mental health education in colleges and universities. After comparing the classification results with the known categories in the test set, the accuracy rate was found to be 75%. Using the alternative error pruning method and test data set, the classification accuracy was 79%, and after PEP pruning was 84%.