Research On Data Mining Of Primary And Secondary School Students’ Psychological Problems Based On Apriori Algorithm

The mental health problems of adolescents have aroused the general concern of the society.Chinese education departments frequently emphasize to strengthen the mental health education of primary and middle school students when issuing policies.The analysis and research of the mental health problems of primary and middle school students have become the focus of attention of scholars at home and abroad.Therefore,taking the psychological problems of primary and middle school students as the research object,the correlation analysis is carried out,and the association rule mining technology is tried to apply to the analysis of the psychological problems of primary and middle school students,which will have certain practical significance for the psychological health guidance of primary and middle school students.Many scholars have done related research on the psychological problems of primary and secondary school students.But most researchers still use conventional statistical analysis methods or use student mental health management systems,which only reflect the surface of mental health data.Some scholars also use traditional data mining algorithms,such as the classic Apriori algorithm or its variants,to analyze the correlation between relevant psychological data.However,in the face of big data,it still has the disadvantage of low efficiency.In the mining process,every item is regarded as equally important,resulting in unsatisfactory mining effect.Therefore,this thesis proposes an improved Apriori algorithm in order to improve the efficiency and accuracy of data mining for psychological problems,aiming at the shortcomings of Apriori algorithm in psychological data mining.In addition,the traditional statistical analysis method of psychological problems can not excavate the internal relationship among the factors affecting psychological problems,but the improved Apriori algorithm proposed in this thesis can excavate the relationship among the factors,so as to better grasp the characteristics of the factors affecting students’ psychological problems in different dimensions and types.It is helpful to analyze the causes of psychological problems and put forward some countermeasures.This thesis first explains the status quo of data mining in the study of psychological problems data,and then expounds the Apriori algorithm commonly used in this kind of data mining,and improves the two key shortcomings of this algorithm.Firstly,in order to solve the problem that the Apriori algorithm ignores the importance degree between different items,weighted rules are introduced to reflect the importance difference between different items from the two aspects of frequency and weight,which greatly reduces the generation of invalid association rules.Second,when the input data set is scanned,the candidate set generates statistical synchronization with supporting values,and instead of utilizing the original input data set in each iteration,the updated input data set is computed by removing useless transactions and items;Finally,combining optimized Apriori with Apache Spark,a new weighted Apriori algorithm based on Spark(WABS)is proposed.Compared with the latest similar algorithms,the experimental results show that this algorithm can effectively shorten the mining time and is conducive to the discovery of more valuable information.Finally,the improved Apriori algorithm is applied to the data mining research on the psychological problems of primary and secondary school students.By using the psychological assessment data of primary and secondary school students,the improved mining algorithm is used for mining.According to the mining results,several rules and characteristics of the existence of psychological factors of primary and secondary school students are analyzed.In order to provide some guidance for students’ mental health education.