Aggregation of web search engines based on users' preferences in WebFusion
Knowledge-Based Systems
Information retrieval from the web: an interactive paradigm
MIS'05 Proceedings of the 11th international conference on Advances in Multimedia Information Systems
| Hi-index | 0.00 |
A novel ranking method named as QueryFind, based onlearning from historical query logs, is proposed to predictusers' information needs and reduce the seeking time fromthe search result list. Our method uses not only the users'feedback but also the recommendation of a source searchengine. Based on this ranking method, we utilize users'feedback to evaluate the quality of Web pages implicitly.We also apply the meta-search concept to give each Webpage a content-oriented ranking score. Therefore, thetime users spend for seeking out their required informationfrom search result list can be reduced and the more relevantWeb pages can be presented. We also propose anovel evaluation criterion to verify the feasibility of ourranking method. The criterion is to capture the rankingorder of Web pages that users have clicked from the searchresult list. Finally, our experiments show that the timeusers spend on seeking out their required information canbe reduced significantly.