Research on the Optimization Path of Data Mining Algorithms and Strategies for Mental Health Education in Colleges and Universities under the New Quality Productivity Framework

Abstract The emergence of mental health problems of college students is mainly closely related to a variety of factors, and it is crucial to conduct in-depth research and provide scientific and effective mental health services to maintain the physical and mental health of college students. Under the framework of new qualitative productivity, data mining technology is utilized to obtain mental health education data, item set is set for its dataset, and Apriori algorithm is utilized to define the support degree, confidence degree, and strong association rules. Using the association rule model, the current situation of mental health education in colleges and universities is explored, and the corresponding optimization path is proposed. Among all the itemsets, {Obsessive Compulsive, Anxiety}→{Study Stress} has the highest confidence level, with a value of 0.9031, and its corresponding support level is 0.1888, which means that obsessive-compulsive disorder and anxiety are the most important reasons leading to students’ study stress in order to cultivate students’ healthy psychology.