-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hello Thomas,
IMO, yes, you should feed it some ham, but don't worry about keeping the ratio even or close. I'd suggest feeding it some ham that has positive scores from time to time, say one ham for every 20-30 spam. That ratio seems to be sufficient for me -- Bayes is doing a wonderful job here. Bob Menschel Tuesday, July 29, 2003, 1:31:14 PM, you wrote: TC> All - TC> I have trained Bayes using about 1000 ham and 2000 spam. As time goes on, I TC> am feeding Bayes false negatives (spam that slipped through). If I get to TC> the point where there are several thousand spam and only the original 1000 TC> ham will it screw up Bayes? In other words, do I need to keep the ham:spam TC> ratio even or anything like that? -----BEGIN PGP SIGNATURE----- Version: PGP 8.0 iQA/AwUBPydc/ZebK8E4qh1HEQLT/ACeLj3LubQbkM81uIFppleB0bLSYeUAoJ9N tbJVtUM02cvLnbZIPZ4FTdwC =Zj9t -----END PGP SIGNATURE----- ------------------------------------------------------- This SF.Net email sponsored by: Free pre-built ASP.NET sites including Data Reports, E-commerce, Portals, and Forums are available now. Download today and enter to win an XBOX or Visual Studio .NET. http://aspnet.click-url.com/go/psa00100003ave/direct;at.aspnet_072303_01/01 _______________________________________________ Spamassassin-talk mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/spamassassin-talk
