[Spambayes] More spam than ham

amedee at amedee.be amedee at amedee.be
Sat May 20 01:22:02 CEST 2006

> A twist for me,
> Spambayes has been so good at finding HAM that it no
> longer identifies HAM as unsure or SPAM. I'm still
> getting spam that sometimes shows as HAM so I train
> it as such.
> Now I get this notice:
> "Warning: you have much more spam than ham -
> SpamBayes works best with approximately even
> numbers of ham and spam."
> How do I deal with this? should I find old emails known
> to be good and paste the raw header/message info
> into the "Train on a message" window?
> Since so much is accurately coming in as HAM but
> SPAM is eternaly new, how do I best bolster the
> trained HAM emails ratio?


I'm just a "dumb" user like you, but in my humble opinion:
if you are confident that there are no false positives and you are happy
the way Spambayes is working for you: ignore that message.
If you really want it to train on additional ham, train it on new ham, not
on old ham. Because if you train sb on ham older than a few months, it
might start to think that old dates always mean ham, and I have seen spam
with forged dates...
I could be totally wrong, but that's my "dumb user" impression of spambayes.

Amedee Van Gasse

More information about the SpamBayes mailing list