Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Big data analytics at North Carolina State University

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
1,584
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on May 19, 2011

This video shows a demonstration of a project where NC State and the IBM jStart team applied analytics to large amounts of unstructured data -- big data -- to find suitors for the university to license their patents to.

  • likes, 0 dislikes

Link to this comment:

Share to:

Uploader Comments (IBMetinfo)

  • We first used a dictionary of several hundred company names, then we added natural language processing rules to identify names not in a predefined list. For example, words starting with capital letters followed by "Inc.", "Corp", "Company", "LLC", "S.A.", "plc", "Ltd.", etc. There might be some false positives, but refining the rules can reduce them.

    The ICA tool can recognize whether a document is of a particular language. So if needed, special language specific rules could be defined.

see all

All Comments (3)

Sign In or Sign Up now to post a comment!
  • how does IBM Content analytic recognize whether it's a company name or just a random name (considering we might deal with other languages)

    moreover, do you have a link for a video or just steps explanation of creating the keywords? is it a must to have IBM Language ware in order to create those key words? thx

Loading...

Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more