A new approach to identify dropout learners based on their performance-based behavior

Abstract

Distance learning environments are increasingly offering more comfort to both learners and teachers, allowing them to carry out their academic tasks remotely, especially in critical times where it is difficult, or even dangerous, to bring these actors together in one physical place. Nevertheless, These same environments are complaining about the massive dropout numbers among their learners. Therefore, designing new intelligent systems capable of reducing these numbers becomes imperative. This paper proposes a new approach capable of identifying and assisting endangered learners experiencing difficulties by monitoring and analyzing their behavior inside the e-learning environment. By building dynamic models to follow the learners’ current situation, the proposed approach could intervene autonomously to save learners identified as struggling. Relying on distributed artificial intelligence instead of humans to closely monitor learners within distance learning environments can be very effective when identifying struggling learners. Furthermore, targeting these learners with early enough and carefully designed interventions can reduce the number of dropouts.