الفهرس | Only 14 pages are availabe for public view |
Abstract A great amount of information is becoming available and daily increasing on the World Wide Web (WWW). In order to fit people’s query with a degree of almost no human decision being interacted, a need for a search engine intelligent enough to automate human reaction arises to properly define his request and how to respond to it. A system that is able to do that should provide knowledge base simulating user’s demand of information retrieval. A model for a search engine’s knowledge base intelligently representing the natural relationships between searching keywords and different domains of searching is introduced in this paper. Article classification, one important component for setting the knowledge base of the proposed model, is the phase that uses current knowledge to support an estimate for classifying the article among different domains. The classification process is a decision making approach based on the fuzzy set theory to give a best estimate in the universe of knowledge data sets. The goal of the classifying phase is to make a decision of which domain will be best a parent to the topic under concern. Furthermore, a list of related topics would be produced along with the level of accepting the article as a child. Hence, article classifier could be viewed as an Article to Domains Association (ADA) generator. |