Original Post
I've spent some time thinking about fun software projects to do in my spare time when I was inspired by the spam flooding my inbox. I think I want to try to make my own spam filter classifier. It probably won't be as good as others you can find online, but I think it might be a good way to learn about bayesian networks. In order to try a classifier, I need a large corpus of spam emails. Does anyone know of a site I can go to to sign myself up for a boatload of spam? I want to set up about 20 honeypot gmail accounts to do nothing but collect the latest spam and then use one of those libraries that lets you use gmail as a disk to get the spams and mount a realtime defense. Probably won't get this far, but I like the idea.