Exploring Student Expectations and Preferences Regarding Online Adaptive Revision: Implications for the Successful Design of Personalized Learning Systems

Abstract

To better understand students’ needs regarding personalized revision, we explored their expectations of adaptive learning and evaluated their experiences with flipped learning throughout a semester. This study builds upon previous research that identified Moodle as the most effective online assessment platform, with the goal of developing an Personalized Exam Revision (PER) plug-in for Moodle. By integrating theoretical frameworks such as Technology Acceptance Model (TAM), Unified Theory of Acceptance and Use of Technology (UTAUT), DeLone and McLean, as well as the Kano model, we developed a unique conceptual model that guided the design of our questionnaire. We then analyzed survey data gathered from students at Chouaib Doukkali University. Adopting an original mixed-methods approach we integrated Principal Component Analysis (PCA), followed by the K-means clustering algorithm to optimise the separation of groups, as well as Natural Language Processing (NLP), to derive meaningful insights from the data. The findings provide valuable insights into students’ requirements, preferences, and satisfaction levels, as well as the impact of Moodle on their learning process. Based on these results, we propose strategic recommendations for developing an adaptive revision module that aligns with students’ actual needs, ensuring that our Moodle plug-in is developed in the right direction to effectively enhance the assessment process.