An evaluation of SimRank and Personalized PageRank to build a recommender system for the Web of Data

The Web of Data is the natural evolution of the World Wide Web from a set of interlinked documents to a set of inter-linked entities. It is a graph of information resources inter-connected by semantic relations, thereby yielding the name Linked Data. The proliferation of Linked Data is for sure an opportunity to create a new family of data-intensive ap-plications such as recommender systems. In particular, since content-based recommender systems base on the notion of similarity between items, the selection of the right graph-based similarity metric is of paramount importance to build an effective recommendation engine. In this paper, we re-view two existing metrics, SimRank and PageRank, and in-vestigate their suitability and performance for computing similarity between resources in RDF graphs and investigate their usage to feed a content-based recommender system. Finally, we conduct experimental evaluations on a dataset for musical artists and bands recommendations thus com-paring our results with two other content-based baselines measuring their performance with precision and recall, cat-alog coverage, items distribution and novelty metrics