RecSim: A Model for Learning Objects Recommendation using Similarity of Sessions

Tiago Wiedmann (University of Vale do Rio dos Sinos (UNISINOS), Brazil)

Jorge Luis Victória Barbosa (University of Vale do Rio dos Sinos (UNISINOS), Brazil)

Sandro José Rigo (University of Vale do Rio dos Sinos (UNISINOS), Brazil)

Débora Nice Ferrari Barbosa (FEEVALE University, Brazil)

Abstract: A learning object (LO) is any entity or resource that can be used in computer-aided learning. This can take the form of text, multimedia content, presentations, programs or any other type of digital content, generally made available through web portals or distance learning systems. The LOs consulted by a student while accessing such portals are related to the interests of the student for the duration of the session. This article proposes a model for LOs recommendation using similarity of sessions, called RecSim. The model receives the sequence of LOs consulted during the current user session along with sessions whose sequences are similar to the LOs consulted in the current session. LOs found in similar sessions are then recommended to the user. A prototype was developed and applied into two controlled experiments. The results were encouraging and show potential for implementing RecSim in real-life situations.

Keywords: learning objects, recommendation systems, similarity analysis

Categories: L.1.2, L.3.0, L.3.2