Microsoft challenges Google's PageRank algorithm

Microsoft is challenging Google’s PageRank algorithm. Microsoft researchers recently published a white paper proposing a new method for computing page importance.

by Helen Leggatt

Called BrowseRank, the new method will use user behaviour data to create a ‘user browsing graph’. Instead of number and quality of links, BrowseRank will use the number of times a user visits a site and the time spent browsing it to denote 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 is important," states the report. "With this graph, we can leverage hundreds of millions of users' implicit voting on page importance."

Looking at data comparing results between PageRank and BrowseRank algorithm search results it’s apparent that social networking sites are featuring more in BrowseRank, assumedly due to the traffic and the time spent on such sites. How “useful” these sites are for searchers is debatable as is, for that matter, their importance.

Tags: algorithm, PageRank, search marketing

Comments (5)

Email to a friend

Print this article

Subscribe to BizReport

Comments

oh great think... but is it possible to implement in practically

Posted by: krishna on July 30, 2008 07:38

Wouldn't this actually reward pages that inconvenienced users by making the content they were looking for take longer to find while punishing the sites that make using the site easier? The only subset to benefit from this system are community sites.

Posted by: Andrew on July 30, 2008 16:53

Indeed, if such a thing were implemented widescale and proven to be a ranking factor, then user journeys and experience would be elongated by site owners looking to gain an edge and this would of course, be informed by the level of traffic sent by the engine in the 1st place! Things like bounce rates and times spent on the page/site I suspect, are already used by the Google algo via information gleaned from analytics and its toolbar. In this respect this whole browserank thing is nothing worth shouting about. MSN looking for airtime methinks. :)

Posted by: rob on July 30, 2008 18:05

This has been tried before, DirectHit had a search engine built entirely on clickstream data (Acquired by Ask.com in 2000). They got the data from ISPs in those days. The end-result is really not that much better than Page-Rank. Me.dium on the other hand (http://me.dium.com/search) is processing user's clickstream data in real-time to create a different lens based on what's going on now. e.g. do a search for John Edwards on Google or Live, and you get johnedwards.com and wiki/johnedwards. Do the same search on Me.dium and you learn that today people care about his love child, pictures of his mistress, etc. The difference is real-time (what people are browsing now) vs. historical (what they browsed in the past). Social vs. Old School. Check it out. http://me.dium.com/search.

Posted by: Chris on July 30, 2008 22:48

I'm not sure this is such a good idea either. Rewarding pages that effectively slow users down seems nonsense. We may find people creating massive pages with overwhelming content rather than organising data more effectively in smaller bite-sized chunks.

Posted by: Alfie on August 4, 2008 11:10