Recommendation method based on learner profile and demonstrated knowledge

The COVID-19 pandemic is increasingly gaining popularity when discussing e-learning in the context of institutional and organizational learning because of its numerous benefits which make it possible for learners to learn regardless of the circumstances and/or the timing. Therefore, the expanding dominion of online learning has caused problem in terms of determining adequate learning activities for the learner in this context, and it relatively becomes a widely used learning technique for learners. Several studies in online learning focused mainly on increasing student achievements based on recommendation systems. An ideal recommender system in e-learning environment should be built with both accurate and pedagogical goals. To address this challenge, we propose a recommendation method based on learner preferences and knowledge level using machine learning technique. The learning approach is designed based on this technology to build a personalized e-learning scenario by selecting the most adequate learning activities for the learner. Moreover, several experiences were conducted in the real environment to evaluate our system. The results show the quality of learning and the learner's satisfaction.