2004 | OriginalPaper | Chapter
A Web Page Scoring Method for Local Web Search Engines
Authors : Yohei Ikawa, Kunihiko Sadakane
Published in: Database Systems for Advanced Applications
Publisher: Springer Berlin Heidelberg
Included in: Professional Book Archive
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Web-page scoring is a method to improve Web search-engines by assigning a score to each page according to its importance. The PageRank algorithm implemented for Google is a well known efficient scoring method for WWW search-engines, whereas it is not efficient for searching a local Web. For the latter case, text matching is usually used for computing scores and the hyperlink structure of Web-pages is wasted. Although a method for scoring local Web-pages called the HotLink method has been proposed, it is not well established because the scores depend on how to extract a tree structure, which is unknown, from the Web-graph.In this paper, we solve the problem of the HotLink method by considering all shortest-path trees and taking the average score. As a result, the scores are independent of the selection of a tree, which makes the scores robust. We also propose an efficient algorithm to compute this average score in O(|V||E|) time where V and E is the set of pages and hyperlinks of a local Web-graph, respectively. Experimental results show that our new scoring method captures important pages in a local Web.