« Benchmark Natural Search vs. Paid Search Traffic | Main | Randy Pausch Last Lecture: Advanced Education for Search Marketers »
July 25, 2008
Microsoft's BrowseRank Aims for Better Results than PageRank
While Google is busy rolling out a PageRank update, Microsoft is researching what they hope will be the next big thing in search: BrowseRank. The technology takes user browsing habits into account when determining relevant search results.
We propose computing page importance by using a 'user browsing graph' created from user behavior data. In this graph, vertices represent pages and directed edges represent transitions between pages in the users' web browsing history. Furthermore, the lengths of staying time spent on the pages by users are also included. The user browsing graph is more reliable than the link graph for inferring page importance.
You can read the full paper by Microsoft Asia researchers here (pdf).
Earlier, we reported that Steve Ballmer says that search needs innovation. Will BrowseRank achieve that goal? Let us know what you think by leaving a comment.
via CNET
Posted by Nathania Johnson on July 25, 2008 12:30 PM
Comments
Robin Majumdar July 25, 2008 10:01 PM
Both ranking mechanisms rely on the same theory : human are better than machine to extract the relevance of information.
For google, human comes through the links on the webpage they produce. The more a page is cited, the more is should be relevant (roughly speaking). For Microsoft, human comes from their browsing and behaviour data. The first stay on data that is easy to extract and the second on data that can be collected in very large amount and which should be more accurate since it is directly related to search (assuming that the behaviour data comes out of the engine). As ever, the best ranking will certainly be an hybrid between those two models.
One remark : both data comes in a way or another from people which build and use the data on the internet... how to make a lot of money simply by using the results of others.
MisterP July 28, 2008 11:51 AM
Very interesting, although 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.
We at Me.dium on the other hand (http://me.dium.com/search) are processing our 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 and let us know your thoughts. http://me.dium.com/search.
Chris July 28, 2008 1:52 PM
This might be the break through needed to challenge google. But many will have privacy concerns.
Cricket Bats September 15, 2008 3:37 AM
Sure, BrowseRank will help take social ranking (which Google has done and perfect on the algorithm level) to the next level.
Witness the Digg / Google deal in the rumour mill... of course the writing is on the wall, but mainly because both MSFT and GOOG can appreciate the true potential of the Facebook datamining opportunities and how it could make targeted advertising something on a whole other level.