You may need to expound a little more on your SpamAssassin setup.
You cannot run sa-learn as root and have it do diddly. You must
run it per user, generally.
{^_^}
----- Original Message -----
From: "Ricardo Kleemann" <rica...@americasnet.com>
To: <users@spamassassin.apache.org>
Sent: Saturday, 2009, February 07 19:46
Subject: not seeing any advantage to sa-learn?
Hi,
I have SA working very well for me, but there are still a few cases of spam
that are very persistent, I still get a considerable amount of spam that SA
doesn't catch.
However, what is annoying is that no matter how much I feed through
sa-learn, the SA score doesn't change much.
I created a folder sa-learn where every day I'll put in the spam that is not
caught, and once a day I have a cronjob that automatically feeds the
messages to sa-learn, and every day I get the confirmation that X messages
were learned.
There are some messages from certain places that I get every single day, of
course I could easily just block by subject but I would like to have SA be
able to catch it and that's why I specifically use sa-learn on a daily
basis.
Maybe it's something to do with my configuration, I don't know.
I'm running spamc/spamd 3.2.4 on a Ubuntu 8.04 server, it's the standard
Ubuntu package. I have the default settings for Bayes (with auto_learn) and
I'm using a mysql backend for BayesStore.
I don't have really any customized settings, I'm just using the
out-of-the-box Ubuntu settings, except for configuring bayes with mysql.
So anyway, what does it take for sa-learn to actually start changing the
score so that eventually I can get the correct classification?
I can send some samples if desired.
Thanks
Ricardo
