should I change score for Bayes_90?

Chris Yuzik chris at
Fri Oct 17 17:25:35 IST 2003

I'm getting quite a number of spam messages that just sneak under the
threshold of 5.0. While I'm tempted to just decrease the threshold, I don't
want to increase the number of false-positives either.

I notice that in each of these messages, Bayes_90 is triggered, but that only
adds 3.0 to the score. If Bayes is 90% certain that this message is spam,
should I "trust" it a little more by say, giving it a 4.0 weight instead of


More information about the MailScanner mailing list