SemreX: Efficient search in a semantic overlay for literature retrieval

The World Wide Web is growing at such a pace that even the biggest centralized search engines are able to index only a small part of the available documents on the Internet. The decentralized structure, together with the features of self-organization and fault-tolerance, makes peerto-peer networking an effective information-sharing model; however, content searching still remains a serious challenge of large scale peer-to-peer networks. In this paper we present SemreX, a semantic overlay for desktop literature/ document retrieval in peer-to-peer networks. We present a semantic overlay algorithm by which semantically similar peers are locally clustered together, and long-range connections are rewired for a short-cut in peer-to-peer networks. Based on the semantic overlay, a heuristic query routing algorithm is proposed for efficient content searching. We conduct a comprehensive simulation to evaluate the search performance of our algorithms. Results show that search in our SemreX semantic overlay greatly improves search efficiency. c © 2007 Elsevier B.V. All rights reserved.