Affiliation:
1. Shaheed Rajguru College Delhi University, India
Abstract
This chapter explains the multi-agent system for effective information retrieval using information scent in query log mining. The precision of search results is low due to difficult to infer the information need of the small size search query and therefore information need of the user is not satisfied effectively. Information Scent is used for modeling the information need of user web search session and clustering is performed to identify the similar information need sessions. Hyper Link-Induced Topic Search (HITS) is executed on clusters to generate the Hubs and authorities for web page recommendations to users who search with similar intents. This multi-agent system based on clustered query sessions uses query operations like expansion and recommendation to infer the information need of user search queries and recommends Hubs and authorities for effective web search.
Reference131 articles.
1. Context-sensitive modeling of web- surfing behaviour using concept trees.;S.Acharyya;Proceedings of the 5th WEBKDD Workshop,2003
2. A Multi-Agent Based Personalized Meta-Search Engine Using Automatic Fuzzy Concept Networks
3. Multicomputers: message-passing concurrent computers
4. Dynamic personalization of web sites without user intervention
5. Improving information retrieval precision using query log mining and information scent.;P.Bedi;Journal of Information Technology,2008