Analysis of Students' Learning Behavior under Network Learning Environment

The emergence of new technologies makes online learning platforms flourish. Although learners can break through the limitations of time and space and choose any resource to learn according to their own pace, there is a problem of low learning pass. This paper attempts to take the Computer Basic online course offered by the university in Yunnan Province on the platform of Superstar as an example, and uses the statistical methods to mine the learners' behavior under the network environment, so as to help stakeholders to better implement teaching and learning, and solve the problem of poor learning effect. This study first adopts Spearman correlation analysis on the learners' online learning behavior, and then uses multiple linear regression analysis method to explore which factors affect comprehensive score, and finally makes clustering analysis on six variables representing learners' behavior to obtain behavior characteristics with similar learners. The research shows that: (1) Learners can be divided into four different groups according to the behavior indicators; (2) Course video progress and chapter learning times have a positive and significant impact on comprehensive score. Through data mining and learning behavior analysis, teachers can identify the characteristics of learners, and then carry out personalized teaching.