Exploring user-based recommender results in large learning object repositories: the case of MERLOT

Collaborative filtering (CF) techniques have proved to be effective in their application to e-commerce and other application domains. However, their applicability to the recommendation of learning resources deserve separate attention as seeking learning resources can be hypothesized to be substantially different from selecting information resources or products for purchase. To date there are only a few scattered studies reporting on the application of well known user-based CF algorithms to learning object repositories. This paper reports an empirical study carried out by using MERLOT data and existing user-based CF algorithms. The aim of this preliminary study was that of finding evidence on accuracy measures of existing CF algorithms, and the relation of the items recommended with other elements of the repository. The results can be used as a starting point for future studies that account for the specific context of learning object repositories and the different aspects of preference in learning resource selection.