Schema-agnostic ranking of RDF properties

In many Semantic Web applications, having RDF predicates sorted by significance is of primarily importance to improve usability and performance. In this paper we focus on predicates available on DBpedia, the most important Semantic Web source of data counting 583 million English triples. We address the problem by associating to each DBpedia property (also known as predicates or attributes of RDF triples) 9 orig- inal features specifically designed to provide sort-by-importance quan- titative measures, automatically computable from an online SPARQL endpoint or a RDF dataset. By computing those features on a number of entity properties, based only on their labels, we created a learning set and tested the performance of a number of well-known learning-to-rank algorithms. By only requiring property labels and with no knowledge on the data ontology and structure, our approach is schema-agnostic and applicable on very different RDF datasets, as we show in the paper. Our experimental results show that the approach is effective and fast, im- proving the ranking quality over the two existing approaches found in literature related to RDF property ranking.