A preference ordered classification to leader learners identification in a MOOC
Sarra Bouzayane, Inès Saad · Journal of Decision System · 2016
This paper presents a methodology relying on the DRSA approach (Dominance-based Rough Set Approach) so as to make a multi-criteria decision about the classification of a Massive Open Online Course (MOOC’s) learner in one of the two preference-ordered decision classes: Cl1 for ‘Not Leader Learners’ and Cl2 for ‘Leader Learners’. This methodology is based on two phases: the first aims at inferring a preference model while the second consists of classifying the MOOC’s learners in one of the two decision classes 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 family of criteria for learners’ characterization and the third is to infer a preference model resulting in a set of decision rules. This methodology is periodically implemented at the beginning of each current week of the MOOC using data of the previous week. It has been validated on real data of a French MOOC proposed by a business school in France.