[Spambayes] Training

Monte montejw at earthlink.net
Tue Jan 10 05:15:37 CET 2006


I've been running SpamBayes for a couple days now, it's getting better 
pretty fast.  Does it do anygood to "train" on messages that are already 
classified correctly?  I'm asking because if I "Review Messages...." and 
there are lots of correctly classified messages and a few new 
unclassified or incorrectly classified messages it trains faster if I 
"discard" the correct ones and only train on the others.  BUT, it's 
easier to just correct the few and leave the others as is.

So, does it do any good to retrain on the correct ones, or does it just 
take a little extra time.

Thanks,
Monte


More information about the SpamBayes mailing list