Introducing linked open data in graph-based recommender systems

Thanks to the recent spread of the Linked Open Data (LOD) initiative, a huge amount of machine-readable knowledge encoded as RDF statements is today available in the so-called LOD cloud. Accordingly, a big effort is now spent to investigate to what extent such information can be exploited to develop new knowledge-based services or to improve the effectiveness of knowledge-intensive platforms as Recommender Systems (RS). To this end, in this article we study the impact of the exogenous knowledge coming from the LOD cloud on the overall performance of a graph-based recommendation framework. Specifically, we propose a methodology to automatically feed a graph-based RS with features gathered from the LOD cloud and we analyze the impact of several widespread feature selection techniques in such recommendation settings. The experimental evaluation, performed on three state-of-the-art datasets, provided several outcomes: first, information extracted from the LOD cloud can significantly improve the performance of a graph-based RS. Next, experiments showed a clear correlation between the choice of the feature selection technique and the ability of the algorithm to maximize specific evaluation metrics, as accuracy or diversity of the recommendations. Moreover, our graph-based algorithm fed with LOD-based features was able to overcome several baselines, as collaborative filtering and matrix factorization.