Matt Kettler <[EMAIL PROTECTED]> wrote:
> If the bayes database doesn't have 200 ham messages in it's learning
> database, the use of the bayes engine will be completely disabled
> until it has.
>
> Now, SA does have autolearning, but in general it rarely auto-learns
> a ham message. So it will take a long time for it to pick up 200 hams
> on
> auto-learn alone unless you've got a lot of email being sent to you
> from places using bonded sender, habeas SWE or similar strong
> negative scoring rule.

Fwiw, most people who keep messages in folders have a ready source of
ham to feed to sa-learn.  I got around this (well, I fed sa-learn the
required 200 hams) by issuing the command

     sa-learn --ham --mbox mail/archive/*

This alone feed 300+ messages to sa-learn.


Also, I routinely issue the command
     sa-learn --ham --mbox /var/spool/mail/cbarnes
after checking my inbox to make sure there are no false negatives, but
before actually reading/deleting my new email.


--

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Chris Barnes                                       AOL IM: CNBarnes
[EMAIL PROTECTED]                            Yahoo IM: chrisnbarnes
Computer Systems Manager                               ph: 979-845-7801
Department of Physics                                 fax: 979-845-2590
Texas A&M University





-------------------------------------------------------
This SF.Net email sponsored by: Free pre-built ASP.NET sites including
Data Reports, E-commerce, Portals, and Forums are available now.
Download today and enter to win an XBOX or Visual Studio .NET.
http://aspnet.click-url.com/go/psa00100003ave/direct;at.aspnet_072303_01/01
_______________________________________________
Spamassassin-talk mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/spamassassin-talk

Reply via email to