Title: Harnessing user contributions and dynamic profiling to better satisfy individual information search needs

Authors: Roman Y. Shtykh, Qun Jin

Addresses: Networked Information Systems Laboratory, Faculty of Human Sciences, Waseda University, Japan. ' Networked Information Systems Laboratory, Faculty of Human Sciences, Waseda University, Japan

Abstract: In the situation of information overload we are experiencing today, conventional web search systems taking a one-size-fits-all approach are often not capable of effectively satisfy individual information needs. To improve the quality of web information retrieval, we propose a collaborative personalised search approach that makes an attempt to |understand| and better satisfy the information needs for each and every searching user. We present a web information retrieval framework called Better Search and Sharing (BESS) that captures user-system interactions, profiles them and induces personal interests that changes over time with an interest-change-driven profiling mechanism that is also extensively used for the co-evaluation of documents found valuable inside a specific search context by users with similar interests.

Keywords: collaborative search; personalised search; relevance feedback; dynamic user profiling; subjective index; subjective vertical search; concept-directed vertical search; user contributions; web search; internet; information retrieval.

DOI: 10.1504/IJWGS.2008.018492

International Journal of Web and Grid Services, 2008 Vol.4 No.1, pp.63 - 79

Published online: 25 May 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article