Study of Procrastination in Higher Vocational Education Based on Online Learning Data

Abstract

Academic procrastination is a common phenomenon in China's higher vocational education. Due to the weakening of the role of teacher supervisors and the lack of students' self-control, the academic procrastination of students in online learning is more likely to occur. At present, it has become a trend to use educational data mining and artificial intelligence technology to evaluate, predict and intervene in online learning, so as to solve the problem of practical teaching lag and improve the teaching effect of vocational education. In this paper, the data of "Computer Application Foundation" course of higher vocational students on Chaoxing platform is used to process the data by using K-means and DBSCAN clustering algorithms, and the performance of the two algorithms is evaluated by using the contour coefficient. The results show that the K-means algorithm has better performance. The students were divided into active learners, mild procrastinators and severe procrastinators by K-means clustering algorithm. Then, combined with decision tree (DT), neural network (NN) and Naive Bayes (NB) algorithm to verify the accuracy of K-means clustering algorithm in identifying the classification of students' procrastination tendency, this paper hopes to provide some advises for online learning procrastinators and encourage students to keep learning initiative and enthusiasm.