[Spambayes] "Blank" Emails clogging my inbox.

[Eric A. Silver]

I've got mine set to 90, and I get about 30 or 40 false positives every day,
including every single message addressed to Spambayes.
I retrain every week, sometimes twice a week.  I retrained today, and
fifteen minutes later had two false positives, both from senders that were
in the Inbox and on my safe senders list.

I have a separate folder called Spambayes and my outlook settings are set to
take any message with Spambayes in the subject line and put it in the
spambayes folder.  Despite that, every message that contains Spambayes in
the subject line ends up in the Junk folder.

When I clear out my junk mail, and ensure that my inbox and junk mail folder
each contain ham and spam, respectively, and then retrain, it doesn't take
very long before I have false positives in my junk mail folder.  Moving an
item from junk to inbox by recovering it from Spam has no apparent effect on
how Spambayes will treat similar mail in the future.  (this includes my list
of safe senders as well.)

Always open to ideas,
Eric A. Silver

-----Original Message-----
From: spambayes-bounces at python.org [mailto:spambayes-bounces at python.org] On
Behalf Of Richard B Barger ABC APR
Sent: Thursday, November 03, 2005 12:19 PM
To: SpamBayes mailing list
Subject: Re: [Spambayes] "Blank" Emails clogging my inbox.


Perhaps no one should be as brave or foolhardy as me, but my Spam Cutoff is
0.39, and I never have a false positive -- and I've been running SpamBayes
for 18 months.  Because of odd circumstances, I get a huge volume of mail,
so I think it's a pretty good test.

Rich Barger

---

"Coe, Bob" wrote:

> I suspect your 90% cutoff is too high. I've been running at 75% for a long
> time, and I can't remember the last time I saw a false positive. I could
> probably drop it another 10 points without significant effect.
>
> Bob
>
> > -----Original Message-----
> >
> > Subject: [Spambayes] "Blank" Emails clogging my inbox.
> >
> >
> >       Over the past 2 weeks, I've been getting 12+ of these
> > blank emails a day.  Every one I mark as spam bumps the level
> > a but higher, but they're not high enough to be automarked as
> > spam (90% is my setting).  I know there are very few tokens
> > in the email, but is there anyway to force them up higher?
> > Outlook can't seem to filter these emails either by using
> > rules or their Junk Mail Rules.
> >

_______________________________________________
SpamBayes at python.org
http://mail.python.org/mailman/listinfo/spambayes
Check the FAQ before asking: http://spambayes.sf.net/faq.html