Re: qsf

On 01/11, Anthony Campbell wrote:
> >From my limited experience so far, I'd say run qsf and spamprobe
> together. Currently I'm using spamprobe to catch whatever qsf misses,
> which is about 5 or 6 a day after very limited training (about 150
> spams). They seem to complement each other well. I'm seeing no spams at
> all and no false positives. 

Wait, you're saying that if either of them flags an email as spam, you
believe them?  So you're effectively just... doubling your false positive
rate?

I do run two filters together - spamprobe and spamassassin.  But the
way I do it, if they agree it's spam it goes to a spam folder and I
never look at it.  If they agree it's not spam it goes to my inbox.
If they disagree it goes to a folder named after the one that caught it,
and I check those folders for false positives.  Works wonderfully.  Don't
think I've ever had a false positive from both on one email, and they
rarely both miss a spam.  (This filtering is done in procmail.)

But the advantage there, I believe, is in the fact that they are two
different types of filters.  Any benefit from running two filters as
similar as spamprobe and qsf (both multi-word token bayesian filters) I
would have to assume could be achieved by using just one with a different
configuration.  

How did you find qsf?

-- 
"Blessed are the cracked, for they shall let in the light."
http://www.ChaosReigns.com

-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV