Users opinions about Learning Object Recommendations: a case study

The enormous growth of learning objects on the internet and the availability of preferences of usage by the community of users in the existing learning object repositories have opened the possibility of testing the efficiency of different techniques on recommending learning materials to the users of these communities. In this work, we focus on some particular parameters at the recommendation phase (different similarity algorithms), evaluating the new recommendations not only via offline analysis but also taking into account users feedback. It has been performed a online analysis over a small group of users. The recommendations were presented to these users along with a small inquiry form about each recommendation. Through this study we tried to find out which algorithm performs better from the online analysis and if it is possible to notice a similarity between the results obtained from the offline and online analysis.