Analyzing instructional quality and students’ reviews of massive open online courses (MOOCs) through systematic and sentiment analyses based on Big data

Abstract

Online education has gained increasing attention from researchers in different fields. Because it expands learning space and has a great impact on teaching methods and education models. In China, the popularity and advocacy of MOOCs are also evident. While MOOCs also face several challenges with low engagement, satisfaction, and utilization rate of high-quality online resource. There is limited study in the areas of analyzing instructional quality of MOOCs. The study, based on the observation for management specialty on CUM, aims to investigate the instructional quality of MOOCs through capturing and analyzing learner reviews from CUM. Combining both quantity and qualitative method, the study integrates word frequency analysis, semantic analysis, and sentiment analysis on learner reviews to present an learner-centered analysis. We can obtain the fundamental situation of the instructional quality of online courses, identify learners’ needs, and present suggestions for improvement.