Efficient Methodologies to Determine the Relevancy of Hanging Pages Using Stability Analysis. Issue 5 (3rd July 2016)

• Record Type: Journal Article
• Authors: Kumar, P. Ravi; Leng, Alex Goh Kwang; Singh, Ashutosh Kumar; Mohan, Anand
• Is Part Of: Cybernetics and systems. Volume 47:Issue 5(2016)
• Page Start: 376
• Page End: 391
• Publication Date: 2016-07-03
• Subjects: Anchor text -- eigenvector and eigenvalues -- hanging pages -- hanging relevancy -- information retrieval -- PageRank -- stability analysis; Cybernetics -- Periodicals; System theory -- Periodicals; 003.5
• DOI: 10.1080/01969722.2016.1187030
• Languages: English
• ISSNs: 0196-9722

Abstract

ABSTRACT: This article presents an algorithm to determine the relevancy of hanging pages in the link-structure-based ranking algorithms. Recently, hanging pages have become major obstacles in web information retrieval (IR). As an increasing number of meaningful hanging pages appear on the Web, their relevancy has to be determined according to the query term in order to make the search engine result pages fair and relevant. Exclusion of these pages in ranking calculation can give biased/inconsistent results, but inclusion of these pages will reduce the speed significantly. Most of the IR ranking algorithms exclude the hanging pages. But there are relevant and important hanging pages on the Web, and they cannot be ignored. In our proposed method, we use anchor text to determine the hanging relevancy, and we use stability analysis to show that rank results are consistent before and after altering the link structure.