[LRUG] Anti-spam measures

Paul Dix paul at pauldix.net
Thu Nov 27 08:35:12 PST 2008


This article outlines a really good approach. It catches a lot and
doesn't get in the way of most users. It's also really simple.
http://nedbatchelder.com/text/stopbots.html

After briefly reading about Courtenay's solution, I don't think it's
that good. It's too much effort and requires too much hand
configuration. You'd be much better going with a naive bayes
classifier (like in Lucas Carlson's Classifier gem or my Basset gem).

I haven't touched Basset in a while and it can be a little confusing,
but you can find it on github here:
http://github.com/pauldix/basset/tree/master

I'd say the best first line is to follow the steps in that first post.
If you're still having spam problems then break out the big guns with
naive bayes.

Best,
Paul


On Thu, Nov 27, 2008 at 10:38 AM, Chris Lowis <chris.lowis at gmail.com> wrote:
> Thanks guys! A lot of ideas there for me to work through. I'll write
> something up to compare them if I end up trying more than one of these
> options.
>
> Cheers,
>
> Chris
>
>
>
> --
> Chris Lowis
> http://blog.chrislowis.co.uk/
> _______________________________________________
> Chat mailing list
> Chat at lists.lrug.org
> http://lists.lrug.org/listinfo.cgi/chat-lrug.org
>



More information about the Chat mailing list