On Sat, 21 Apr 2012, John ffitch wrote:
On Sat, 21 Apr 2012, RW wrote:
That's what use_bayes 0 is for.
Unless you really have to, turning-off Bayes is a bad idea. The FP rate
is much higher without it.
Beyes does not make much sense in a multi-user, diverse community such as my
university department. Makes sense here (small company; small user base)
==John ff
I'll have to disagree with that, as a person running a mail server for a
university college (organizational unit bigger than a department) which has
thousands of users. Bayes may not be as deadly accurate as it would in a
totally homogeneous environment but still worthwhile.
Altho the ham may be all over the ball-park, the spam tends to cluster in
waves. Also Bayes is as much about the headers as it is the body and so
will find commonalities that aren't obvious at first glance.
FWIW I run a site-wide bayes with auto-learning and occasional hand
training. Maybe not optimal but still worth doing and doesn't need much
attention. Over the past 9 years I've had to discard my Bayes database and
start from fresh (due to going totally off the rails) -once-.
--
Dave Funk University of Iowa
<dbfunk (at) engineering.uiowa.edu> College of Engineering
319/335-5751 FAX: 319/384-0549 1256 Seamans Center
Sys_admin/Postmaster/cell_admin Iowa City, IA 52242-1527
#include <std_disclaimer.h>
Better is not better, 'standard' is better. B{
