Examination of student satisfaction with e-courses by clustering analysis

Abstract

Student satisfaction is one of the foremost factors for e-courses to continue efficiently and achieve their goals. The present research aims to analyze the clustering tendencies of e-course students’ satisfaction with e-courses according to the variables of “gender, class, computer ownership, computer and internet literacy, duration of internet use, the connection type to the internet, and the tools utilized by the students in the learning management system” through clustering algorithms, one of the data mining techniques. The survey model was employed. A 35-item satisfaction scale devised for students taking e-courses was used for data collection. A total of 522 students taking online courses at a university participated in the study. Descriptive statistics and cluster analysis were employed to analyze and interpret the data. As a result of the analyses through K-Means cluster analysis, four different clusters were obtained. Those clusters were defined in accordance with the variables they included as follows: Cluster 1 (the group with the highest rate of computer ownership and the highest computer literacy); Cluster 2 (the group with the lowest rate of computer ownership and the lowest computer literacy); Cluster 3 (students have low computer literacy and low duration of Internet use), and Cluster 4 (the group with the highest rate of females, first graders, and those who use the Internet at “good” and “very good” levels) . According to the research results, the mean student satisfaction levels regarding e-courses were determined to be low in general. As per the clustering analysis, it was observed that the students in Cluster 1 and Cluster 4 had the highest mean values of satisfaction with e-courses and a “good” level of satisfaction compared to the other groups, while Cluster 2 had the lowest mean value. Cluster 3, on the other hand,  was the one with a “medium” level of satisfaction.