A Collaborative Framework for Customized E-Learning Services by Analytic Hierarchy Processing

Thanks to the drastic proliferation of the Internet, e-learning has been recognized as an effective medium for various kinds of aggressive learners. However, due to the deficiencies of tutoring and guiding functionalities in current learning platforms, casual learners may deviate from the original course direction with frustration, when confronting inflexible course materials and fixed learning models. In the post-COVID-19 era, we believe that the most important functionality for a personal learning environment (PLE) to offer is a course recommendation process which adaptively provides a versatile course combination scheme for different learners from different perspectives. In this paper, we propose a flexible framework for users to customize their e-learning environment based on a two-stage Analytical Hierarchical Processing (AHP) structure for building adaptive course portfolios, which adaptively provides a versatile course scheme for different learners. The main objective of our framework is to transform a learner from a role of passively accepting the course content organized by instructors, into another role of proactively selecting the courses and contributing their knowledge to continuously improve the learning platform. We believe the approach proposed is a versatile way for supporting various challenges for the next generation of personal e-learning environment.