Theme-Based Summarization for RDF Datasets

A growing number of RDF datasets are published on the web. These datasets can be viewed as graphs; querying, analyzing and visualizing such data graphs are critical challenges facing the applications willing to use them, especially when their size is important. Summarization can help addressing these challenges. In this paper, we present a summarization approach which exploits the underlying themes of an RDF graph, and builds a global summary from the theme summaries. To this end, we propose some node relevance metrics. We present some experiments to illustrate the effectiveness of our approach.