Abstract:

Learning analytics (LA) is a rapidly developing interdisciplinary research field. Main goals of LA are to understand learners, understand and optimize learning and the environments in which it occurs, and support decision making in education.
Main objective of our research is to present a new approach to support teachers. In order to improve students’ success as well as predict students at risk, i.e. students who are at greater risk of failing the course, teachers are supposed to use results from decision trees and social network analysis of course activity dynamics from previous academic years. The decision tree method is used for identification of predicted students’ success groups and in particular for selection a group of students whose learning dynamics may lead to undesirable outcomes. The selected group of students is supposed to receive additional attention of teacher in order to increase awareness of their poor performance in the course. Dynamics of predicted success group is analyzed using social network analysis assuming students in the same success group are connected.
We use data of a study progress during monitoring program in an undergraduate statistical course. Demographic profile of students and their performance on other courses were not included in the analyses.

Keywords:

Learning analytics, predictive analytics, students’ success, decision tree, social network analysis.