[Spambayes] Autotraining & definetly delete spam

[Tony Meyer]

> I don't know if, when I click on "delete as spam" or "recover 
> from spam", the bayesian kernel is training by itself.

"Delete As Spam" and "Recover From Spam" both move and train, yes.

> Also, I would like to know if the filtering process includes any 
> kind of autotraining, in order to reinforce its database of 
> spam/ham tokens.

No.  Filtering classifies only, it doesn't do any training.

> Second, definitely deletion of messages.
> 
> I think that messages with a score higher than a certain 
> level should be definitely deleted in Windows, Outlook.

Please see FAQs 3.9 and 3.11 and this sf tracker:

<http://spambayes.org/faq.html#how-can-i-configure-spambayes-to-delete-spam-
rather-than-moving-it>
<http://spambayes.org/faq.html#why-can-t-i-set-spam-to-be-moved-to-the-delet
ed-items-folder>
[ 774650 ] Additional post-filtering options
<http://sourceforge.net/tracker/index.php?func=detail&aid=774650&group_id=61
702&atid=498106>

=Tony.Meyer

-- 
Please always include the list (spambayes at python.org) in your replies
(reply-all), and please don't send me personal mail about SpamBayes.
http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this.