Publication details

Course Similarity Analysis

Authors

BYDŽOVSKÁ Hana

Year of publication 2016
Type Article in Proceedings
Conference Proceedings in Informatics and Information Technologies
MU Faculty or unit

Faculty of Informatics

Citation
Field Informatics
Keywords course similarity; student performance prediction; university information system
Description Courses offered to students at universities have different characteristics. In this paper, we analyse course similarities to improve the students’ performance prediction. We utilize the item-to-item collaborative filtering approach that computes course similarities based on students’ grades. We also use content based techniques to compute course similarities based on the information from the course catalogue, e.g. the course content or prerequisites. Using the computed similarities and utilizing different clustering algorithms, we are able to reveal interesting course groups that can be used to improve the student performance prediction. Finally, we are able to predict the students’ final grades of the investigated course by examining grades of only three related courses.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info