Chris Beggy on Thu, 23 Jan 2003 16:41:03 -0500 |
"Arthur S. Alexion" <arthur@alexion.com> writes: > On Wed, 2003-01-22 at 13:56, news@kippona.com wrote: >> I'm having good luck with ifile, one of the bayesian filters, >> with spam. My standard is spamassassin with spamass-milter, and >> ifile seems more effective and faster. >> >> Here's a link to a recent conference: >> >> http://spanconference.org/ Oops: http://spamconference.org/ > How does it compare to bogofilter (if you've tried that too)? I haven't tried bogofilter, but it seems great. EMR mentioned in his presentation at the conference that the training set is more important than the algorithm for determining performance. Chris _________________________________________________________________________ Philadelphia Linux Users Group -- http://www.phillylinux.org Announcements - http://lists.netisland.net/mailman/listinfo/plug-announce General Discussion -- http://lists.netisland.net/mailman/listinfo/plug
|
|