SBLWPR – similarity based link weight for pagerank calculation

Abstract

Search engine retrieves list of web pages which are relevant to the given query from the index and sorts the list based on the page importance score. There are different ranking algorithms available in the literature to calculate the importance score of web pages. The basis of all ranking algorithms is the link structure of the web. In existing ranking algorithms, no weight is assigned to the links by considering the similarity among the linked documents. Since links from similar documents are more important than the links from other dissimilar documents, a new method is introduced to assign weight to each link based on the similarity among the linked documents. Calculated link weight is added with existing PageRank value to calculate final PageRank. Proposed technique is compared with existing ranking algorithms using the measures precision, recall and F-measure.