Agent and ontology based information gathering on restricted web domains with AGATHE

Abstract

Due to Web size and diversity of information, relevant information gathering on the Web is a very complex task. The main problem with most information retrieval approaches is neglecting the context of the pages, mainly because search engines are based on keyword indexing. Considering restricted domain, the policy of taking into account context may lead to more relevant information gathering in this paper, a specific cooperative information gathering approach based on the use of software agents and ontologies is proposed. To implement this approach, a generic software architecture, named AGATHE system, based on early prototype, the MASTER-Web system, permitting development of specific restricted-domain information gathering systems is presented in detail, with a focus on the extraction subsystem.