282 Int. J. Metadata, Semantics and Ontologies, Vol. 8, No. 4, 2013 Copyright © 2013 Inderscience Enterprises Ltd. An improved semantic information searching scheme based multi-agent system and an innovative similarity measure Djamel Nessah* Computer Science Department, Abbes Laghrour University, Khenchela 40002, Algeria Email: nhdjamel@yahoo.fr *Corresponding author Okba Kazar Computer Science Department, Laboratoire d’Informatique Intelligente, Mohamed Khider University, Biskra 07000, Algeria Email: kazarokba@yahoo.fr Abstract: The key task for the web, namely, web searches, is evolving towards some novel form of semantic web search. In fact, most information retrieval systems are based on static vectors representations. Two major difficulties when a researcher uses current information retrieval systems are how to filter out irrelevant documents, and how to discover latest or more significant documents. Recently a very promising approach to semantic web search is based on combining standard web pages and search queries with ontological background knowledge. In this perspective we will describe a model to hold a document’s noise, and incompleteness. For this, we merge a syntactic keyword search with purely semantic search based domain ontology and a multi-agent system to solve such distributed problems. Then we perform a ranking algorithm on returned documents, and we propose a new semantic similarity measure between concepts based on the WordNet taxonomy structure. Keywords: semantic information search; multi-agent system; semantic web; web languages; ontology; semantic annotation; metadata; inference engine; similarity measure; WordNet. Reference to this paper should be made as follows: Nessah, D. and Kazar, O. (2013) ‘An improved semantic information searching scheme based multi-agent system and an innovative similarity measure’, Int. J. Metadata, Semantics and Ontologies, Vol. 8, No. 4, pp.282–297. Biographical notes: Djamel Nessah received his Master’s degree in Computer Science, Artificial Intelligence from Abbes Laghrour University, Khenchela, Algeria in 2009. Actually he is a PhD student in Computer Science and an Assistant Professor at the Faculty of Sciences and Technology, Khenchela, Algeria. His research interests include semantic web application-based multi-agents systems. Okba Kazar is a Full Professor at Computer Science Department in Biskra University. He obtained his Master’s degree in 1997 from Constantine University (Algeria) working on artificial intelligence field. He obtained his PhD degree from the same university in 2005. He is member of editorial board of some international journals and author of some publications in international journals. He participates as a member of programme committee in international conferences. He is interested and working in artificial intelligence field and multi-agents systems, and advanced information systems. 1 Introduction Traditional techniques applied in many information systems and query processing are based on independent keywords and are unable to represent the semantic of the document’s content, whereas, information retrieval systems based on structured text representation can improve the recall and the precision measurements by taking into account the context and semantic categories. Today the web becomes an immense source of heterogeneous and dynamic information that requires the implementation of powerful tools to retrieve useful information