Creation of semantic overlay networks based on personal information

Abstract

In P2P systems, nodes typically connect to a small set of random peers to query them, and they propagate those queries along their own connections. To improve that mechanism, Semantic Overlay Networks influence those connections depending on the content of the peers, clustering peers in overlapped groups (Semantic Overlay Networks). Ontologies are used for describing semantic information of shared items and user profile. Once the peers are grouped by their semantic information, we can take advantage of that distribution to add some new functionalities as recommendation. In this paper we focus on the description and evaluation of SONAtA, a SON classifier algorithm to globally organize peers into semantic groups, executed locally in each peer. © 2009 Springer Berlin Heidelberg.