X
2008

Microsoft Slams Google PageRank With BrowseRank

July 29, 2008 0

“Standing just far-off third position to Google, Microsoft is confident that it can teach its competitor a thing or two about searching the Internet. Google’s PageRank, the popular Web site-ranking system is being challenged by Microsoft.”

Microsoft researchers have recently released reports that describes the new system for determining which Web pages are the most relevant for a given keyword search query.

 

Microsoft claims that its new tool called: “BrowseRank,” can deliver better search results by measuring user behavior; including where users go and the amount of time they remain at those pages.

Microsoft states that PageRank does not take into account frequency and staying time of Web site visits, while BrowseRank monitors user behavior data to calculate page importance.

The greatest part of Google’s rise to search engine leadership was an algorithm called PageRank that assesses a specific page’s importance by how many other Web pages link to it and by the importance of those linking pages. But of late, Microsoft researchers and academic collaborators detailed an idea this week it calls BrowseRank that seeks to bring more of a human touch to that assessment.

“The more visits of the page made by the users and the longer time periods spent by the users on the page, the more likely the page are important. We can leverage hundreds of millions of users’ implicit voting on page importance.” And so claims the findings of some Microsoft researchers in partnership with some Asian academic fellows in a research report on BrowseRank: Letting Web Users Vote for Page Importance.

“The more visits of the page made by the users and the longer time periods spent by the users on the page, the more likely the page are important. We can leverage hundreds of millions of users’ implicit voting on page importance,” the researchers said in BrowseRank: Letting Web Users Vote for Page Importance, a paper from the SIGIR (Special Interest Group on Information Retrieval) conference this week in Singapore.

The academic paper was co-authored by Microsoft Research Asia researchers Bin Gao, Tie-Yan Liu, and Hang Li; Zhiming Ma of the Chinese Academy of Sciences; Yuting Liu from Beijing Jiaotong University; Shuyuan He from Peking University; and Nankai University’s Ying Zhang.

Search is enormously importance to the Internet for many reasons. For one thing, search engines are highly powerful middlemen that steer users to Web sites they may not be able to find on their own. For another, queries typed into search engines can be influential — and in Google’s case highly profitable — indications of what type of advertisement to place next to the search results.

However, Google’s branded PageRank system only measures the relative importance of Web pages through the use of a sequence of data-processing instructions — called a link analysis algorithm — that assigns a numerical weighting to each element within any given set of hyperlinked documents.

“Pages that we believe are important pages receive a higher PageRank and are more likely to appear at the top of the search results,” Google said. “We have always taken a pragmatic approach to help improve search quality and create useful products, and our technology uses the collective intelligence of the Web to determine a page’s importance.”

But Microsoft researchers disagree that PageRank has a number of flaws. For one thing, people can game the system by building bogus Web sites called link farms. Those sites feature hyperlinks point to a Web page whose importance a person wants to inflate so it appears higher in search results. Another PageRank concerns is that the indexing process does not take into account the time a user spends on a particular site.

But user behavior, monitored in anonymous form by Web servers and Web browser plug-ins, can be better, the authors states.

“Experimental results show that BrowseRank can achieve better performance than existing system, including PageRank…in important page finding, spam page fighting, and relevance ranking.”

Microsoft and its academic collaborators mention that their new system is superior because it is based on a user-browsing graph that is generated from data that reflects actual human behavior. “User-behavior data can be recorded by Internet browsers at Web clients and collected at a Web server,” they said.

BrowseRank’s user-browsing graph can more accurately represent the Web surfer’s random walk process, and thus is more useful for calculating page importance, the collaborators claim. Furthermore, the amount of time spent on the pages by users is also included under the BrowseRank method.

“In this way, we can collect hundreds of millions of users’ implicit voting on page importance,” researchers explained.

But Microsoft trails behind leader Google and No. 2 Yahoo in search. It is struggling hard to catch up, for example with unsuccessful proposals to acquire Yahoo or its search business that would cost the company billions of dollars. And Microsoft just bought search start-up Powerset.

“And not to mention the smart Google is not putting all its eggs in the PageRank basket, though.”

“It is important to keep in mind that PageRank is just one of more than 200 signals we use to determine the ranking of a Web site,” the company said in a statement. “Search remains at the core of everything Google does, and we are always working to improve it.”

For all its flaws and disadvantages, Google’s PageRank would still remain an industry accepted standard for a lot of things relating to website importance and values. And it would take more than user behavior analysis to disprove its importance and accuracy. In fact, we are already anticipating another round of Google page rank update in the coming days.