Microsoft dreams up a new kind of search with BrowseRank

A group of Microsoft researchers just presented a paper about a concept called BrowseRank that could really shake up the search landscape.

As the name implies, BrowseRank is Microsoft’s new take on Google’s PageRank algorithm — namely, the method Google uses to rank pages in its search results, based primarily on links. Obviously, Google’s approach is pretty darn effective, and must be grappled with by any company hoping to make money on the Web. But there are flaws, says a team of Microsoft researchers based in China. For one thing, it’s so easy to make a link that sites try to trick Google by creating things like link farms to boost their ranking. For another, links don’t tell you how long a user looked at a page, or how valuable the page was to them.

That’s where BrowseRank comes in. Instead of using PageRank’s “link graph,” the new ranking system would use a “user browsing graph.” By visiting a page and spending a lot of time on it, users would be implicitly “voting” for the pages that deserved to be ranked more highly.

It’s a compelling idea, albeit a scary one, since it would upend the way companies get attention online. (A Google spokesperson told CNET that PageRank is only one of more than 200 “signals” used to determine a site’s rank.) Microsoft is also trying to improve its MSN Search service in other ways, most notably with the recent acquisition of semantic search company Powerset. If Microsoft can actually make good on some of the promise behind these deals and ideas, it might be able to reverse MSN Search’s slide towards irrelevance. In the long-term, I certainly think that improving its technology is a much better strategy than offering to pay people to use its search engine.

Of course, there’s a huge gap between an academic paper and an actual product. But hey, that’s how Google started.

Next Story: Analyst predicts merger of Android and Symbian mobile OSs
Previous Story: Microsoft acquires DATAllegro data warehouse appliance company

Bookmark and Share

Tags:

Photo of Anthony Ha

About the Author, Anthony Ha

Anthony is VentureBeat's assistant editor, as well as its reporter on enterprise technology, cloud computing, and tech policy. Before joining VentureBeat in 2008, Anthony worked at the Hollister Free Lance, where he won awards from the California Newspaper Publishers Association for breaking news coverage and writing. He attended Stanford University and now lives in San Francisco. Reach him at anthony@venturebeat.com. You can also follow Anthony on Twitter.

  • Aashay
    "By visiting a page and spending a lot of time on it, users would be implicitly “voting” for the pages that deserved to be ranked more highly."

    I don't know about you, but I find this to be a little strange. Some websites suck, and so it takes longer to find information on their pages. In fact, I'd say that the quicker I can find information on a page, the more useful the website. I sure hope their algorithm considers that, otherwise there are going to be lots of turds floating up to the top of the rankings.
  • Jeff
    The articles mentions how people can trick Google by developing link farms, etc. It seems to me you could equally trick this new concept by setting up a thousand computers, directing them all to the same site, and constantly leaving them on... www.gothamtechminute.blogspot.com
  • This has actually already been done in the legal search space by PreCYdent (www.precydent.com).

    It shouldn't be suprising that PreCYdent was the first to solve the problem. Judges put their clickstreams into their opinions in the form of citations.

    As an aside, PreCYdent is also the first portfolio company for Venetian Capital Management.
  • Jojo
    Well, I'd like to see something change. Google search results have deteriorated for me over time. Many times when I search for things, I wind up with first page links to garbage sites like NextTag, PriceGrabber, CNET, Dealtime, etc. that are mainly price comparison pages with precious little useful (or valid) information. I'd like to see these types of pages somehow banished off the first few Google pages unless you specifically searched for say "price comparison".
  • Jason
    Sounds like a great idea. I think I could be persuaded to use Live Search if this kind of feature existed.
  • The FAROO P2P Search Engine has been doing this for some time already:
    "FAROO takes the user behavior when viewing a page into consideration for ranking. This is done automatically, without requiring a manual rating from the user. Thus for the first time the user as audience of a page also decides about its ranking."
    http://www.faroo.com/english/technology/archite...
  • With this rank you can trick also. Just stay on you own webpage a couple of minutes at the background for example.
  • I am, Omar Jareño, the original author of the article: "BrowseRank Microsoft's "dream" to confront the PageRank" in Spanish: "BrowseRank de Microsoft "sueña" con plantarle cara al PageRank")

    Can see on the website: http://www.puromarketing.com/8/4884/browserank-... in the web PuroMarketing.com

    That you so blatant plagiarism, by changing the title and content slightly

    I demand to put my name as the original author as well as links to the original web PuroMarketing.com

    The copyright also exist on the Internet


    Greetings
    Omar Jareño Vargas
    Expert in Marketing on the Internet and ecommerce
    www.OmarJareno.com
    www.CapsulasDeMarketing.com
    http://www.puromarketing.com/page/staff.html
  • Omar, your accusations of plagiarism are baseless and completely untrue. I've never read your article, nor am I fluent enough in Spanish to have plagiarized it. Moreoever, the dateline on your article is July 31, while mine was published on July 25. I'd like to hear how I plagiarized something that wasn't even published when I wrote my piece. Was a time machine involved?
  • I am, Omar Jareño, the original author of the article: "BrowseRank Microsoft's "dream" to confront the PageRank" in Spanish: "BrowseRank de Microsoft "sueña" con plantarle cara al PageRank")

    Can see on the website: http://www.puromarketing.com/8/4884/browserank-... in the web PuroMarketing.com

    That you so blatant plagiarism, by changing the title and content slightly

    I demand to put my name as the original author as well as links to the original web PuroMarketing.com

    The copyright also exist on the Internet


    Greetings

    Omar Jareño Vargas
    Expert in Marketing on the Internet and ecommerce
    www.OmarJareno.com
    www.CapsulasDeMarketing.com
    http://www.puromarketing.com/page/staff.html
  • I am, Omar Jareño, the original author of the article: "BrowseRank Microsoft's "dream" to confront the PageRank" in Spanish: "BrowseRank de Microsoft "sueña" con plantarle cara al PageRank")

    Can see on the website: http://www.puromarketing.com/8/4884/browserank-... in the web PuroMarketing.com

    That you so blatant plagiarism, by changing the title and content slightly

    I demand to put my name as the original author as well as links to the original web PuroMarketing.com

    The copyright also exist on the Internet


    Greetings

    Omar Jareño Vargas
    Expert in Marketing on the Internet and ecommerce
    www.OmarJareno.com
    www.CapsulasDeMarketing.com
    http://www.puromarketing.com/page/staff.html
  • edhardy622
    UGGs became ubiquitous among Southern California surfers and Southern California downhill skiers, and from there, Uggs, which name comes from the Australian
    http://www.uggboots365.co.uk
  • 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.
  • asfasfasfas
    social search kinda sucks you know? because i hate to limit my search to those of my friends