XRank: Learning More fromWeb User Behaviors

Link analysis has been widely used to evaluate the importance of web pages. PageRank, the most famous link analysis algorithm, offers an effective way to rank the pages. However, the algorithm ignores three facts. First, nowadays the way that users retrieve information is quite different from the previous way when web search engine was not extensively used. Second, inter-site links and intra-site links should not be treated equally. A link from a different site is more important for a page than that within the same site. Third, most users start their browsing from a homepage, which should be given more weight than other pages. In this paper, we propose a novel ranking algorithm called XRank as a solution to these problems. Experimental results on the CWT100g show that our XRank algorithm outperforms other famous ranking algorithms, including PageRank and Two-Layer PageRank, especially on sites recommendation and web spam avoidance.