Online (web-based) courses emerged at the beginning of the twenty-first century. While this new pedagogic paradigm (PP) holds a promise of better learning and training, it comes with challenges as traditional PPs are not suited to the new settings which highly differ from the physical classroom methods. We studied three online PPs (Synchronous, Asynchronous, and Asynchronous with an audience) and their influence on the students learning process and achievements during an academic mathematics course that was conducted online. 168 students took an exam and answered a questionnaire regarding their learning preferences, experience, and habits after experiencing one of these PPs. We found that students who studied according to the asynchronous with an audience PP achieved a higher score in the exam, regardless of their initial level than students who learned by either the synchronous or asynchronous PPs. In addition, we developed a personalized model based on machine learning methods that match an online PP for each student to maximize the student's score in the exam. In the case of an academic mathematical course, the online PP had a major influence on the students' scores in the exam. We found that students with high grades in previous courses preferred synchronous learning, which indicates the importance of picking the right online PP for each student. Our model provides a novel tool for the pedagogic community to personalize online learning by recommending the PP that could be most suitable for each student.
Keywords: Asynchronous learning; Pedagogic machine learning models; Personalizing pedagogic paradigm; Synchronous learning.
© The Author(s), under exclusive licence to Springer Nature Switzerland AG 2022.