User-Adaptive Recommendation Techniques in Repositories of Learning Objects: Combining Long-Term and Short-Term Learning Goals

In this paper we describe a novel approach that fosters a strong personalized content-based recommendation of LOs. It gives priority to those LOs that are most similar to the student's short-term learning goals (the concepts that the student wants to learn in the session) and, at the same time, have a high pedagogical utility in the light of the student's cognitive state (long-term learning goals). The paper includes the definition of a flexible metric that combines the similarity with the query and the pedagogical utility of the LO.