Research on Clustering Mining and Feature Analysis of Online Learning Behavioral Data Based on SPOC

Abstract

As the wide spread of SPOC in colleges and universities, the key point for current educational research in the era of big data is how to use SPOC's record data to analyze and mine learners' learning behavior. This paper uses the record data of more than 700 learners on the SPOC platform of Renai College of Tianjin University, adopts k-means clustering and hierarchical clustering analysis algorithms to mine learners' learning behavior characteristics, Learners are divided into four types: weak cognition, self-consciousness, short-cut and lazy. The analysis results were visualized using 3D andprobability density function graph. This paper aims to explore SPOC behavioral data model and mining algorithms.