@proceedings {
	title = {Weekly predicting the at-risk MOOC learners using dominance-based rough set approach},
	author = {Bouzayane, Sarra and Saad, Inès},
	editor = {Kloos, Carlos Delgado and Jermann, Patrick and Pérez-Sanagustín, Mar and Seaton, Daniel T. and White, Su},
	abstract = {This paper proposes a method based on the Dominance-based Rough Set Approach (DRSA) to predict the learners who are likely to drop out the course during the next week of the MOOC (Massive Open Online Course) based on their demographic and dynamic data of the previous week. These are called "At-risk Learners''. This method consists in two phases: the first aims at inferring a preference model while the second consists of classifying each learner either in the decision class Cl1 of "At-risk Learners'' or in the decision class Cl2 of "Active Learners'' based on the previously inferred preference model. The first phase is made of three steps: the first is to identify assignment examples of learners, the second is to construct a coherent criteria family for the learners' profiles characterization and the third is to infer a preference model resulting in a set of decision rules. The two phases should be weekly implemented throughout the MOOC broadcast. This method has been validated on real data of a French MOOC proposed by a Business School in France.},
	year = {2017},
	month = {05/2017},
	publisher = {Springer International Publishing},
	edition = {1},
	volume = {10254},
	pages = {160-169},
	address = {Madrid},
	country = {Spain},
	doi = {https://doi.org/10.1007/978-3-319-59044-8_18},
	url = {https://link.springer.com/chapter/10.1007/978-3-319-59044-8_18},
	isbn = {978-3-319-59044-8},
	refereed = {yes},
	keywords = {dominance-based Rough Set Approach, multicriteria decision making, prediction, “At-risk Learner” preference model},
}