Naslov
Using descriptive and predictive learning analytics to understand student behavior at LMS Moodle

Autori
Oreški, Dijana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the Thirteenth International Conference on e-Learning / Raspopović Milić, Miroslava - Beograd : Metropolitan University, 2022, 18-24

Skup
The Thirteenth International Conference on e- Learning

Mjesto i datum
Beograd, Srbija, 29.09.2022. - 30.09.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Learning analytics ; educational data mining ; LMS data ; machine learning.

Sažetak
Learning analytics is a data-centric field that applies machine learning algorithms in the educational domain to analyze e-Learning environment data. This study employs descriptive and predictive learning analytics approaches in order to develop descriptive and predictive models of student behavior and success. Cluster analysis, unsupervised machine learning algorithm, and decision tree, supervised machine learning algorithm, are applied on the data from a Learning Management System (LMS) Moodle. Research results indicated: (i) groups of students with similar patterns in behavior at LMS, (ii) student activities at LMS that lead to successful course completion. Such results serve as guidelines for teachers when developing courses and students when enrolling in the course. Descriptive and predictive learning analytics is an innovative approach in education that can enhance teachers and students and improve learning outcomes.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti

POVEZANOST RADA