2. Which gives better results, feeding a large spam and ham archive at once, or starting from scratch let the filter make the decisions and correct it appropriately? I thought that starting from a clean slate and letting the filter make its choices and correcting them will give better results.
This is the approach that Spam Assassin takes. It does not start considering bayes results until some large number of email has been fed to it. I think it is several thousand, but I did not check. It usually takes about 1 week for my email to start getting filtered using bayes criteria, and I receive a couple of thousand emails per day, of which about 150 to 200 are typically spam.
Tom Veldhouse
signature.asc
Description: OpenPGP digital signature
