IdentifyingWeb Spam by Densely Connected Sites and its Statistics in a JapaneseWeb Snapshot

Abstract

Web spamming refers to actions intended to mislead search engines into ranking certain pages higher than they deserve. Recently, the amount of web spam has increased dramatically, leading to a degradation of search results. One of the most effective spamming techniques is link spamming. This is done by setting up an interconnected structure of pages for deceiving link-based ranking methods, such as PageRank. In this paper, we analyze distributions of link spam in our archive of Japanese web pages using link analysis techniques.