On Friday 18 August 2006 01:55, jdow wrote:
> From: "Nigel Henry" <cave.dnb@xxxxxxxxxx>
>
> > I can't say I'm too clued up on the finer points of spam filtering, but
> > am willing to learn. Ideally spam should be stopped at source, but I
> > don't suppose there's much chance of that happening.
Joanne writes.
>
> I can give a data dump.
<big snip>
> {^_-} Joanne
Thanks very much for all the info. I'll file it, and work my way through it.
Regarding your comment that a bayes filter was not sufficient on it's own, I
did see a post on this list a while back, where someone was first filtering
using SA, then followed by a second filtering with a bayes filter, which I
think was "spambayes" (couldn't find that, but think it was supposed to be on
sourceforges site). They claimed that what was missed by SA was picked up by
the second filtering with the bayesian filter, and virtually eliminated all
the spam.
Open season for hunting spammers sounds like a good idea. Just gotta get that
one through congress. Perhaps the NRA will support it. In the UK they banned
fox hunting. Personally I don't think that was a bad thing. After all the
poor old foxes only stole the odd chicken to survive. Now. Replacing that
with spammer hunting. Same hounds, trained to detect the spammers, using spam
samples (not the "Spam" pressed meat). Capture a few spammers, set them
loose, and then set the hounds after them. Great fun.
Nigel.
