Spam sorting (was Re: Install assistance needed in Berkeley area)

[Tim Freeman]

From: Nick Moffitt <nick@zork.net>
>	I don't understand what you're talking about.  It sure doesn't
>sound like any self-reinforcing bayesian filter techniques any sane
>person would use.  How do you let it adapt if you keep a static
>training corpus instead of treating that like an initial seed?

So far I have been only training it on a spam when that spam gets
through the filter, and then on the next non-spam to maintain the
balance between spam and good messages in the corpus.  I might be
changing that.

Expiring old messages is not something I would want to do if my old
good messages and old bad messages were of comparable age, but my good
messages are older on the average.

>	Are you volunteering [to package spambayes]?

Not right now.
-- 
Tim Freeman                                                  tim@fungible.com
I xeroxed a mirror. Now I have an extra xerox machine. -- Steven Wright