• To: 'Joshua Allen' <joshuaa@m...>, xml-dev@l...
• Subject: RE: Data mining the semantic web? (was RE: Semantic Web)
• From: "Bullard, Claude L (Len)" <clbullar@i...>
• Date: Wed, 31 Jul 2002 08:14:11 -0500

As long as you remember:

1.  Ontologies have to be shared; interpretations can still vary.

2.  Information has to be shared.  What you can't see, you can't mine.

3.  A stratified web will return uneven results for given mining efforts.

4.  You have to filter for superstition.  A system that cannot 
    distinguish between identification and classification is not one 
    on which to build quick decision systems.  Metaphorically, don't 
    build fire control systems over URIs.

5.  One wants to combine "opinions of others" with "self-published 
    opinions".  Prediction also relies on self-asserted opinions.

6.  All a data mining effort can return is an informed opinion.

Yeah, DARPA wants it bad.  Has since before there was a web to mine.

len

-----Original Message-----
From: Joshua Allen [mailto:joshuaa@m...]

Completely in agreement with Jonathan here.  This intersection is
interesting to many people it seems: http://www.darpa.mil/iao/ 

• Prev by Date: Ann: Upcoming XSL training in North America, Asia and Europe
• Next by Date: RE: The BBQ Proposition was Re: Re: URIs, concrete
• Previous by thread: RE: Data mining the semantic web? (was RE: Semantic Web)
• Next by thread: RE: Data mining the semantic web? (was RE: Semantic Web)
• Index(es):
  • Date
  • Thread