Not having done a lot of manual training of Bayes until recently I havn't come across this before, but it seems that with some kinds of messages its very difficult to train them as ham and get a sufficiently low BAYES score to make a difference.
These are mainly genuine messages that score between 3 and 5 with no Bayes score, but after repeated training of many similar messages the lowest I can get is BAYES_30.
Since BAYES_30 only gets -0.9 this doesn't really help much at all, compared to -2.6 for BAYES_20 or -4.7 for BAYES_10.
Anybody have any suggestions why almost all the ham I manually train won't budge below BAYES_30 ?
Regards, Simon
------------------------------------------------------- This SF.net email is sponsored by: VM Ware With VMware you can run multiple operating systems on a single machine. WITHOUT REBOOTING! Mix Linux / Windows / Novell virtual machines at the same time. Free trial click here: http://www.vmware.com/wl/offer/345/0 _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
