A model for a collaborative recommender system for multimedia learning material

Abstract

In a cluster of many servers containing heterogeneous multimedia learning material and serving users with different backgrounds (e.g. language, interests, previous knowledge, hardware and connectivity) it may be difficult for the learners to find a piece of material which fit their needs. This is the case of the COLDEX project. Recommender systems have been used to help people sift through all the available information to find that most valuable to them. We propose a recommender system, which suggest multimedia learning material based on the learner's background preferences as well as the available hardware and software that he/she has.