Gaining Insights on Student Course Selection in Higher Education with Community Detection (2105.01589v1)

Abstract: Gaining insight into course choices holds significant value for universities, especially those who aim for flexibility in their programs and wish to adapt quickly to changing demands of the job market. However, little emphasis has been put on utilizing the large amount of educational data to understand these course choices. Here, we use network analysis of the course selection of all students who enrolled in an undergraduate program in engineering, psychology, business or computer science at a Nordic university over a five year period. With these methods, we have explored student choices to identify their distinct fields of interest. This was done by applying community detection to a network of courses, where two courses were connected if a student had taken both. We compared our community detection results to actual major specializations within the computer science department and found strong similarities. To compliment this analysis, we also used directed networks to identify the "typical" student, by looking at students' general course choices by semester. We found that course choices diversify as programs progress, meaning that attempting to understand course choices by identifying a "typical" student gives less insight than understanding what characterizes course choice diversity. Analysis with our proposed methodology can be used to offer more tailored education, which in turn allows students to follow their interests and adapt to the ever-changing career market.