Daniel Carrera wrote:
On Thu, Jul 24, 2003 at 12:00:13AM +0100, Nix wrote:
Spam actually seems to differ quite a lot between individuals,
Really? Why would that be the case? The whole point of spam is that it's
intended for no one in particular and they make no research to find out if
you are at all likely to interested in viaragas, porn or bankers from
Nigera.
Would it be best if I did not borrow spam from other people?
Worked for me. I needed to learn/test spamassassin before rolling it
out on a client's mail server, so I borrowed a bunch of spam to prime
the bayesian filter, and then set up one of the procedures provided to
make it easy for the users to train it once it's deployed. I've now got
a "test stream" from one of their real users forwarding mail to the test
server. SpamAssassin and the bayes filter handle it with no problem.
The design of the system is such that it is intended to adapt to the
changing nature of spam (it drops unused tokens, etc). This is just an
extreme example of the change. So don't make the perfect the enemy of
the good -- borrow some spam. Just don't expect perfection.
-------------------------------------------------------
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
