Massive Open Online Courses – an Adaptive Learning Framework

Diverse student needs present a challenge in online education. Massive Open Online Courses (MOOCs) attract many diverse learners, so there is need to tailor the course instruction to meet the students’ individual needs. This paper investigates an adaptive MOOC system from a personalised learning perspective. Firstly, we review existing literature on adaptive online learning systems, bringing together findings on the relationship to both effective learning support and motivation to study. Secondly, we outline a proposed framework, which tailors the recommendation of instructional material using the learner’s profile. In this model, the system can present the user with a suggested learning path to meet appropriate learning objectives. As the student progresses, further recommendations can be made with appropriate resources to enhance and develop the learner’s understanding of the previous topics. Adaptation and personalised recommendation have been noted as providing the means for an online system to replicate, in part, the function of a human tutor. However, there are drawbacks both in the limitations of providing the best recommendations and in the danger of users having little control over their own learning. Allowing learners to manage their learning by setting objectives and developing paths has been associated with encouraging effective learning skills, increasing collaboration and enhancing learning. Our framework therefore supports users in creating their own paths, allowing them to make informed choices about appropriate resources based on their expression of current objectives and preferences. The framework will be evaluated by adapting an existing MOOC, allowing comparison of a variety of aspects including choice of learning path, learner satisfaction and effect on attainment and drop-out rate. Keyword: Online course, MOOC, instructional course, recommendation, adaptive, responsive, learner preference