Behavioral Patterns of Completers in Massive Open Online Courses (MOOCs): The Use of Learning Analytics to Reveal Student Categories

The learning energy of MOOC completers has important reference value for future learners. Existing research focuses on the behavioral performance of dropouts and participants, but ignores the mining of completer behavior patterns. In this paper, Kmeans clustering method, descriptive statistics, one-way analysis of variance, and chi-square test were used to systematically study the behavioral characteristics and academic performance of 1,388 MOOC completers. The results show that there are significant differences in resource and task preferences, effort levels, and so on, and learners can be divided into hard-working harvesters and punch-in participants; there is no significant difference in demographic characteristics. The article proposes strategies for improving teaching and promoting ordinary learners to improve learner behavior patterns and learning efficiency.