Online Course Refinement through Association Rule Mining

A.Y.K. Chan, K.O. Chow, and K.S. Cheung (PRC)


Online Courses, Web Usage Mining, Association Rule Mining


Online courses are widely used to support teaching and learning in higher education. To improve their quality, instructors must continuously refine them according to the students' needs. Questionnaires may be used to gather student feedback but it is subjective, expensive and time consuming. Web server log files, which are recorded automatically, provide a cheaper and quicker way to gather user access data. However, existing web log analysis software does not provide sufficient or relevant information about student usage in online courses. This paper proposes to refine online courses from student usage pattern through association rule mining. Association rule mining is applied on web server log files of 14 online courses. Results show that the discovery of student usage patterns can be used for the refinement of online courses.

Important Links:

Go Back