Learning actor ontology for a personalised recommendation in massive open online courses

Massive Open Online Courses revolutionised online learning and instigated research on information and communication technologies for learning to enhance the learner experience and increase his engagement level. In earlier research, we identified the recommendation criteria that could be used to recommend suitable MOOCs for the learner's needs and motivations. Thus, criteria like the level of knowledge, competences and the pace of learning introduced by MOOCs and preferred by learners will be matched by a personalised recommender system. In this paper, we model the Learning Actor ontology to be used for this matching process. It is a domain ontology that was developed by following the phases of the on-to-knowledge methodology: feasibility study, kickoff phase, refinement phase, evaluation and validation phase and, finally, the maintenance phase. At last, we obtained the learning ontology that describes the "learning actor" major class by using a complex definition of characteristics and their relationship and range of values.