Social Web Experience for Internet Explorer

Download this episode

Download Video

Description

Today a new experiment comes out of Redmond in the form of a new toolbar for Internet Explorer that analyzes the web pages you are looking at and applies what it sees to your social networks. This means the proper nouns and contextual references in the sites you're looking at are matched up to the things your friends might be talking about. So if you're browsing a movie review, you may see what a friend wrote about that movie as an inline contextual update.

Emre Kiciman and CK Wang from Microsoft Research joined us at the Channel 9 studio to talk about the Social Web toolbar and how it works. You can download the Social Web Experience Toolbar for IE here.

Embed

Format

Available formats for this video:

Actual format may change based on video formats available and browser capability.

    The Discussion

    • User profile image
      prasannap

      1. Would love to ALSO see consolidated list of information for the page that I visit insted of just individual Link that I need to hyperlink

       

      2. Great tool. Any easy ways I can also get info. about the pages that my friends visit to get their information. I know you DO NOT have to share the info. about who visited which page, but would love to see on a specific day which was the MAX # for all the pages visited within my friend circle

       

      3. Anyway for us to rate the content so that I see the hottest topic at that split moment

       

      In short I would like to see the MOST Important & MOST Valuable information

    • User profile image
      tonyso

      The examples shown here are consumer-focus, when can we see and IT Pro/Dev focus for this? Are the buckets that the tool looks in fixed or programmable?

    • User profile image
      Emre K.dot

      Hi Tony,

       

      What do you mean by buckets?

       

      The matching between social network messages and the web pages is open-ended.   We use 2 algorithms in our tool to do the matching, and 1 is trained on wikipedia and recognizes the kinds of things talked about in wikipedia pretty smartly; the other technique is a context-free matching algorithm on n-grams.  The former gives better results and we rank those matches higher.  But neither technique is limited to consumer scenarios.

       

      I think the trick to getting this to work for specialized scenarios will be making sure that you have the data you care about available in the social network.

       

       

    Comments closed

    Comments have been closed since this content was published more than 30 days ago, but if you'd like to send us feedback you can Contact Us.