Smart media-based context-aware recommender systems for learning: A conceptual framework

Modern technologies have been greatly employed to support teachers and learners for facilitating teaching and learning processes. Recommender systems (RSs) for technology-enhanced learning (TEL) are among those new technologies that have been researched extensively within the past few years. This is because RSs for TEL are intelligent decision support systems that assist internet users in finding suitable learning objects that might match their preferences on the kinds of materials they could require to enhanced their learning activities. However, most of the existing RSs for learning used traditional techniques (2-dimensional user × item, techniques) to recommend learning objects to users without considering the contexts in which the recommendation should be made. Those contexts could be the geographical locations, the level of education, the time of the day or week, their learning preferences, and so on. This paper proposed a conceptual framework of smart media-based context-aware RSs for learning that could consider the learning preferences of users as a context for making accurate and usable recommendations. The proposed system was designed to run on smart devices for learners to test and know their learning styles and receive learning object recommendations according to their learning preferences. The paper contains the conceptualization of the framework and the details of the design and implementation procedure.