Boris Chidlovskii, Nathalie Glance, Antonietta Grasso
Proc. AAAI-2000 Workshop on AI for Web Search, July 30, 2000, Austin, TX
In this paper we present a system architecture for coupling user and community profiling to the information
search process. The search process and the ranking of relevantdocuments are accomplished within the
context of a particular user or community point of view. The user andcommunity profiles are built by analyzing
document collections put together by the users and by the communitiesto which the users belong. Such
profiles are used for ranking the documents retrieved during the search process. Inaddition, if the search results
are (implicitly or explicitly) considered as relevant to the user or community, the user/community profiles can
be tuned by re-weighting the profile terms. Both recommender systems and meta-search engines can be
enhanced using this kind of collaborative environment for ranking the search results and re-weighting the user
and community profiles.
Report number: