Re: Case sensitivity in CLASSIFY and LEARN

 
> I'm wondering if the CLASSIFY and LEARN statements are case
> sensitive.  If so, does that mean I have to convert all texts into
> the same case before feeding them into the CLASSIFY and LEARN
> statements to achieve higher accuracy (without training with all
> possible combinations of cases for each word)?

Case is a form of syntactic data that is highly relevant for spam
classification and most likely relevant for any other given form of
categorization as well. For example, the word 'free' can be perfectly
innocuous in itself, but when it appears capitalized or in all caps,
the document in which it appears is more likely to be Spam. When used
in the context of the word 'radicals' the document is suddenly more
likely to be about health than it is politics or arm-wearying viewing
material.

You aren't going to train CRM114 on word lists anyways, you'll use
documents that are representative of the traffic you're planning to
analyze.

Best,
Chris

-- 


Make a difference in the world and support more Diplomacy projects and
services then you can shake a dagger at, please read:

http://members.bluegoosenews.com/diplomacy/blog/2008/09/24/a_special_note_for_diplomacy_players
 - or - 
http://tinyurl.com/3wx6lb 

Blue Goose is willing to give me $250 to support various services and
projects in the Diplomacy hobby. The blog post above will tell you why
they are doing this, what I will do with the money, and what you can do
to help me get it.

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/