Abstract
Data on the web has grown insanely large to the point that humans cannot deal with using traditional tools. Hence the need for adequate tools to filter such huge amount of information and extract only the useful part has risen. Collaborative Recommender Systems based on Collaborative Filtering are one of the de facto tools for such purpose. Their primary goal is to suggest the suitable items for the appropriate users. However, due to the lack of information about the new entities, these systems may suffer from what is known as the cold start problem. In this work, we propose a solution to overcome the main case of cold start problem, namely new item problem. For that, we propose to use the Linked Open Data in the hope to find enough information about new items, thus bridge the gap between the recommender system and available data. We report on some promising experiments of the proposed solution performed on MovieLens data sets.