on Sun Jul 29 2007, skip-AT-pobox.com wrote: > >> Have you tried lowering your spam threshold a bit? > > Dave> No, I haven't tried that. I suppose I run the risk of a few false > Dave> positives if I go too far with that? > > Take a look at the scores in the spams marked unsure and in any hams which > are marked unsure. You might well be able to lower the spam threshold a > fair amount without running the risk of too many (if any) false positives. > > I use: > > [Categorization] > ham_cutoff:0.20 > spam_cutoff:0.7
OK, I have some hams that scored as high as 0.85 Is everything between the ham_cutoff and spam_cutoff classified as unsure? Moving my spam_cutoff to 0.86 probably would make only a small dent in my results. -- Dave Abrahams Boost Consulting http://www.boost-consulting.com The Astoria Seminar ==> http://www.astoriaseminar.com _______________________________________________ SpamBayes@python.org http://mail.python.org/mailman/listinfo/spambayes Check the FAQ before asking: http://spambayes.sf.net/faq.html
