From: Gawnsoft <xlucid@...>
Date: 2003-07-24T04:47:50+09:00
Subject: Re: Ruby Spam Corpus

On Wed, 23 Jul 2003 07:42:27 +0900, Daniel Carrera
<dcarrera@math.umd.edu> wrote (more or less):

>-----BEGIN PGP SIGNED MESSAGE-----
>Hash: SHA1
>
>Hi all,
>
>90% of my spam comes from ruby-talk.
>I have begun using SpamAssassin and I'm trying to teach it enough spam so 
>the Bayesian filter can kick in.
>
>Does anyone have a corpus of spam I can use?  Ideally it'd be a corpus of 
>spam routed through ruby-talk which is the one I'm trying to get rid of.

I have a corpus of about 750 spams (HGH viagra, get rich quick, etc)
which I've been collecting for the day I bother to get an email client
that does bayesian filtering.  Very few, if any, have arrived from the
ruby-talk list.

You're welcome to a copy, but the commonest term the Bayesian filter
will identify from it all is my email address!

If you're interested, contact me off-list - there are various
'contact' links at my web-site.



Cheers, 
   Euan
Gawnsoft: http://www.gawnsoft.co.sr
Symbian/Epoc wiki:  http://html.dnsalias.net:1122
Smalltalk links (harvested from comp.lang.smalltalk)  http://html.dnsalias.net/gawnsoft/smalltalk