Authors:
Ralph Weires
;
Christoph Schommer
and
Sascha Kaufmann
Affiliation:
University of Luxembourg, Faculty of Sciences, Technology and Communication, Luxembourg
Keyword(s):
Information Retrieval, Relevance Feedback, Implicit Feedback, Collaborative Retrieval.
Related
Ontology
Subjects/Areas/Topics:
Data Engineering
;
Ontologies and the Semantic Web
;
Searching and Browsing
;
User Modeling
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
;
Web Personalization
Abstract:
Web search engines often include results for a query which are not really relevant for a user. SEREBIF is an approach for incorporating feeback from the users into the search engine results to increase the result quality. We especially focus on implicit feedback, which does not require the users to put any additional effort than usual into the search process. The captured information (e.g. entered queries, clicked results) is afterwards analyzed, and the results are then taken into account for further search sessions. SEREBIF can generally be used on top of an existing search engine to improve its results. In this paper, we explain the basic idea of SEREBIF, the current state of the prototype we realized and first results.