A model for generating proactive context-aware recommendations in e-Learning systems

A proactive recommender system pushes recommendations to the user when the current situation seems appropriate, without explicit user request. This is suitable in e-Learning scenarios in which a great amount of learning objects are available but it is difficult to find them according to the user's needs. In this paper, we present a model for generating proactive context-aware recommendations in the Virtual Science Hub (ViSH), a educational platform related to the GLOBAL excursion European project. The model relies on domain-dependent context modeling in several categories to generate personalized recommendations to teachers and scientists that will produce the learning resources the students will consume. The recommendation process is divided into three phases. First, the generation of the social context information related to the users in the platform. Then, the current situation considering the social, location and user context is analyzed. Finally, the suitability of particular learning objects to be recommended is examined. Therefore, details about the recommendation model proposed and advantages related to applying the model in ViSH can be found in the paper, in addition to some conclusion remarks and outlook on future work.