Bayes: Worth it?

[Julian Field]

    [ The following text is in the "ISO-8859-1" character set. ]
    [ Your display is set for the "US-ASCII" character set.  ]
    [ Some characters may be displayed incorrectly. ]

I find on my site that it works okay with minimal training from a few
users who know how to do it. Less effective, undoubtedly, but not worthless.

I also keep an archive copy of all the mail used to train it, so if my
Bayes DB gets corrupted or poisoned, it's an easy task to re-teach it
from scratch.

Christian Campbell wrote:

>-----BEGIN PGP SIGNED MESSAGE-----
>Hash: SHA1
>
>
>
>>I then have two shared imap folders that usre drag email to if
>>
>>
>SA gets
>
>
>>it wrong (one ham one  spam). Then I run a daily update to
>>
>>
>retrain.
>
>
>
>If I don't have users drag ham/spam corrections to a shared IMAP
>folder for re-learning, will bayes just be less effective, or
>will it become completely worthless?  A very large percentage of
>my user base will be unable to comprehend and perform the task
>of moving false positives and false negatives to an IMAP folder;
>as simple as it sounds.
>
>
>
--
Julian Field
www.MailScanner.info
Buy the MailScanner book at www.MailScanner.info/store
Professional Support Services at www.MailScanner.biz
MailScanner thanks transtec Computers for their support

PGP footprint: EE81 D763 3DB0 0BFD E1DC 7222 11F6 5947 1415 B654

------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at jiscmail.ac.uk with the words:
'leave mailscanner' in the body of the email.
Before posting, read the MAQ (http://www.mailscanner.biz/maq/) and
the archives (http://www.jiscmail.ac.uk/lists/mailscanner.html).

Support MailScanner development - buy the book off the website!