Sequence-based Approaches to Course Recommender Systems

Abstract

A curriculum is a planned sequence of instructions or a view of the student’s experiences in terms of the educator’s or school’s instructional goals. However, the guidance provided by the curriculum is limited and both student and course counsellor struggle with the question of choosing a suitable course at a proper time. Many researchers have focused on making course recommendations with traditional data mining technologies, yet they failed to take a student’s history path of taking courses into consideration. In this thesis, we study sequence-based approaches for the course recommender system. First, we implement a course recommender system based on three different sequence related approaches: process mining, dependency graph and sequential pattern mining. Then, we evaluate the impact of the recommender system on undergraduate students in higher education. The result shows that all three methods can improve the performance of students in a certain scale while the approach based on dependency graph contributes most.