ONTOSPREAD: A Framework for Supporting the Activation of Concepts in Graph-Based Structures through the Spreading Activation Technique

Abstract

The present paper introduces the ONTOSPREAD framework for the development, configuration, customization and execution of the Spreading Activation technique over graph-based structures, more specifically over RDF graphs and ontologies arising from the Semantic Web area. This technique has been used to the efficient exploration and querying of large and heterogeneous knowledge bases based on semantic networks in the Information and Document Retrieval domains. ONTOSPREAD implements the double process of activation and spreading of concepts in ontologies applying different restrictions of the original model like weight degradation according to the distance or others coming from the extension of this technique like the converging paths reward. This technique provide a whole framework to ease the information access, common required feature in the exploitation of the current Web of Data. Moreover, it is considered to be relevant to support the recommendation of concepts in different fields liked e-health, e-procurement or e-tourism with the objective of getting a set of ranked resources. Finally an evaluation methodology and two examples using ontologies from different domains are provided to validate the goodness, the improvement and the capabilities of this framework applied to digital libraries. © Springer-Verlag Berlin Heidelberg 2013.