High-stake student drop-out prediction using hidden Markov models in fully asynchronous subscription-based MOOCs

Dries Benoit, Wai Kit Tsang, Kristof Coussement () and Annelies Raes
Additional contact information
Dries Benoit: UGENT - Universiteit Gent = Ghent University = Université de Gand
Wai Kit Tsang: UGENT - Universiteit Gent = Ghent University = Université de Gand
Kristof Coussement: LEM - Lille économie management - UMR 9221 - UA - Université d'Artois - UCL - Université catholique de Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique
Annelies Raes: KU Leuven - Catholic University of Leuven = Katholieke Universiteit Leuven

Post-Print from HAL

Abstract: In this study, we analyze the learning behavior of 24,000 students in a fully asynchronous subscription-based MOOC platform using hidden Markov models (HMMs) to examine the relationship between learning motivation and student drop-out behavior. In contrast to previous findings, our results reveal that student drop-out is not necessarily correlated with low motivation, as students may drop out despite being highly motivated at the end of their learning journey. To design more effective student retention campaigns, educational decision-makers must consider the motivation level and target potential drop-outs with a low state of motivation. More specifically, our findings emphasize the need for early intervention to prevent students from dropping out, as it becomes challenging to stimulate motivation once it reaches its lowest state. By adopting our proposed methodology, decision-makers can gain a better understanding of the student drop-out process and make more informed student retention interventions.

Date: 2024-01
References: Add references at CitEc
Citations:

Published in Technological Forecasting and Social Change, 2024, 198, pp.123009. ⟨10.1016/j.techfore.2023.123009⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-04542480

DOI: 10.1016/j.techfore.2023.123009

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().