I am getting a about 2% of my mail that is clean HAM marked as spam by BAYES_99 as being 99-100% spam.
What can I do about it? How does BAYES_99 pick spam? I assume its a baysian filter....
Yes, it's a bayes filter. You can turn it off, or start again, this time seeding it with some manual training to give the autolearner some good ideas to start with.
To disable bayes. see man Mail::SpamAssassin::Conf
To wipe out your bayes DB and start fresh use rm -f ~/.spamassassin/bayes_*. Manualy train using the sa-learn tool. see man sa-learn
