> The Not Spam Option does not seem to function in my case. Once a > source has been tagged as spam – it stays spam.
The button should do two things: (1) move the message back to its original location (or the Inbox if that can't be determined). (2) train the classifier that the message is ham (untraining first if necessary). Is it doing (1) for you? It's harder to judge (2), because you don't really see this training; however, you should notice that classification quickly gets accurate if you continue to train. If it's not doing (1), please try it again (to generate the log entries) and send us a copy of your most recent log (SpamBayes- >SpamBayes Manager->Advanced->Diagnostics->View Log). If it is doing (1), but you don't think it's doing (2) (i.e. it keeps making mistakes), please select a message it misclassifies - before you train it - and choose "Show spam clues for this message" from the SpamBayes menu, and send us the message it creates (with an explanatory note at the top). Because SpamBayes starts out with no knowledge at all, there's no way for us to know what it's making the decisions it is without seeing the clues specific to the training you have done. =Tony.Meyer -- Please always include the list (spambayes at python.org) in your replies (reply-all), and please don't send me personal mail about SpamBayes. http://www.massey.ac.nz/~tameyer/writing/reply_all.html explains this. _______________________________________________ [email protected] http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
