Predicting students’ satisfaction using a decision tree

This research focuses on students’ satisfaction and on how students’ satisfaction relates to their performance and involvement in study activities in the e-classroom. Our research is a case study at the course level of a business and economics study programme at a private higher education institution in Slovenia. The study is based on decision-tree induction, a highly used algorithm in a variety of domains for knowledge discovery and pattern recognition using a data mining approach. The results revealed that students are less satisfied with a course when both the requirements for the involvement in the e-classroom and the workload are both high. Further, the average grade might not be of crucial importance when addressing student satisfaction. In our case, students are much more satisfied with a course when the average grades are high and when the workload is not so elevated and when a part of the workload moves to the e-classroom.