Big data analytics for MOOC video watching behavior based on Spark

The purpose of this study is to measure the effectiveness of courses delivered using MOOCs in China Agricultural University. Video watching is considered to be the most important way to disseminate knowledge in Massive Open Online Course (MOOC). Its mission is to understand the degree of students' learning engagement and to provide suggestions for teachers to construct courses. This paper proposes the analysis methods of students' video watching behavior in MOOCs platform and verifies it with the data of the cauX platform. Initially, a detailed statistical analysis of video watching data and behavior was performed. Later, data preprocessing algorithms based on Spark platform were developed and used to calculate the number of video watching behaviors in every hour and every minute. Then, the entropy weight method was used to calculate the weight of pause video, seek video and speed change video. Finally, we analyze and discuss the results of experiment. The results show that the proposed method based on Spark platform can quickly and accurately analyze the characteristics of video watching behavior.