Abstract: In recent years, MOOC developed well and accumulated massive behavior data in the process of using vast teaching resources. Therefore, big data analytics technology based on MOOC is a new research trend and its frame can be involved in four stages: where to get big data (Where), what are data types of MOOC (What), how to deal with big data (How) and do with applications (Do). The paper arranges research status and describes characteristics and classifications of MOOC, then puts forward a framework of Where-What-How-Do for big data analytics. At last, it designs and displays an experiment with multiple regression analysis and cluster analysis on Canvas Network dataset, and makes conclusions on MOOC data of some insight and applications.


Key words: MOOC, big data analytics, Where-What-How-Do, cluster analysis