Dropout prediction in e-learning courses through the combination of machine learning techniques

Lykourentzou, I; Giannoukos, I; Nikolopoulos, V; Mpardis, G; Loumos, V

dc.contributor.author	Lykourentzou, I	en
dc.contributor.author	Giannoukos, I	en
dc.contributor.author	Nikolopoulos, V	en
dc.contributor.author	Mpardis, G	en
dc.contributor.author	Loumos, V	en
dc.date.accessioned	2014-03-01T01:30:14Z
dc.date.available	2014-03-01T01:30:14Z
dc.date.issued	2009	en
dc.identifier.issn	0360-1315	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/19508
dc.subject	Distance education and telelearning	en
dc.subject	Dropout prediction	en
dc.subject	E-learning	en
dc.subject	Machine learning	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Education & Educational Research	en
dc.subject.other	Distance education and telelearning	en
dc.subject.other	Dropout prediction	en
dc.subject.other	Machine learning	en
dc.subject.other	Machine learning techniques	en
dc.subject.other	Prediction methods	en
dc.subject.other	Probabilistic ensemble	en
dc.subject.other	Simplified fuzzy ARTMAP	en
dc.subject.other	Distance education	en
dc.subject.other	Fuzzy neural networks	en
dc.subject.other	Internet	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Multimedia systems	en
dc.subject.other	Robot learning	en
dc.subject.other	Students	en
dc.subject.other	Teaching	en
dc.subject.other	E-learning	en
dc.title	Dropout prediction in e-learning courses through the combination of machine learning techniques	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/j.compedu.2009.05.010	en
heal.identifier.secondary	http://dx.doi.org/10.1016/j.compedu.2009.05.010	en
heal.language	English	en
heal.publicationDate	2009	en
heal.abstract	In this paper, a dropout prediction method for e-learning courses, based on three popular machine learning techniques and detailed student data, is proposed. The machine learning techniques used are feed-forward neural networks, support vector machines and probabilistic ensemble simplified fuzzy ARTMAP. Since a single technique may fail to accurately classify some e-learning students, whereas another may succeed, three decision schemes, which combine in different ways the results of the three machine learning techniques, were also tested. The method was examined in terms of overall accuracy, sensitivity and precision and its results were found to be significantly better than those reported in relevant literature. (C) 2009 Elsevier Ltd. All rights reserved.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	Computers and Education	en
dc.identifier.doi	10.1016/j.compedu.2009.05.010	en
dc.identifier.isi	ISI:000269069200037	en
dc.identifier.volume	53	en
dc.identifier.issue	3	en
dc.identifier.spage	950	en
dc.identifier.epage	965	en