A Ranking Algorithm via Changing Markov Probability Matrix Based on Distribution Factor

With the rapid growth of the web, it will become more and more difficult to provide relevant information to the users to cater to their needs. The web structure mining plays an important role in this approach. There are two classic ranking algorithms HITS and PageRank commonly used in web structure mining. These two algorithms treat all links equally while assigning rank scores. This paper provides a new ranking algorithm via changing the Markov probability matrix based on distributed factor. This algorithm assigns rank scores based on the similarity of web pages instead of equal assignment. Our experiment results show that our algorithm performs better than the standard PageRank.