[Users] spam filtering for tcltk at perl.org

Dave Howorth dave at howorth.org.uk
Tue Apr 7 12:25:10 CEST 2020


On Sun, 5 Apr 2020 16:10:48 +0100
RW <rwmaillists at googlemail.com> wrote:

> On Thu, 2 Apr 2020 00:34:11 +0100
> Dave Howorth wrote:
> 
> > I'm subscribed to the tcltk at perl.org list and puzzled by how claws
> > behaves with respect to it, or specifically bogofilter. Every
> > message I receive from the list is sent to the 'maybe-spam' folder.
> > I religiously classify it as ham and move it to another folder. But
> > it never seems to learn. There's never been any spam from that list
> > so it shouldn't be confused. It generally seems to classify mail
> > pretty reliably and I don't understand why it has a 'thing' about
> > this particular mail list.
> > 
> > Any ideas? Is there some way I can inspect why it has classified a
> > particular mail as 'maybe-spam'?  
> 
> Try saving one of them before training and piping it through 
> 
>   bogofilter -vvv
> 
> This should tell you what tokens are contributing to the
> classification. If your repeat this after training you can compare the
> results and see if things are moving in the right direction. 

Well, I've now had a new message from the list so I've done this, but I
don't really understand what I'm looking at or how it can help me. I've
attached the bogofilter -vvv output from before and after I classified
it as ham, and the source of the message itself, if anybody can
understand the data.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: after-bogo
Type: application/octet-stream
Size: 40700 bytes
Desc: not available
URL: <http://lists.claws-mail.org/pipermail/users/attachments/20200407/46cce64a/attachment-0003.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: before-bogo
Type: application/octet-stream
Size: 40703 bytes
Desc: not available
URL: <http://lists.claws-mail.org/pipermail/users/attachments/20200407/46cce64a/attachment-0004.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 4
Type: application/octet-stream
Size: 15185 bytes
Desc: not available
URL: <http://lists.claws-mail.org/pipermail/users/attachments/20200407/46cce64a/attachment-0005.obj>


More information about the Users mailing list