Course Similarity Analysis

Varování

Publikace nespadá pod Pedagogickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

BYDŽOVSKÁ Hana

Rok publikování 2016
Druh Článek ve sborníku
Konference Proceedings in Informatics and Information Technologies
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
Obor Informatika
Klíčová slova course similarity; student performance prediction; university information system
Popis 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.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.