> Sorry I wasn't very clear. The results in the hotmail example were > where the users said it wasn't spam but hotmail insisted it was. It > is possible for a user to indentify non-spam as spam. But if a user > says it isn't spam then it isn't no matter how much it might look like > it might be.
Phishing spam leaps immediately to mind as a counterexample; the fact that the user mistakes it for legit mail is exactly the problem. -- Dave Pooser, ACSA Manager of Information Services Alford Media http://www.alfordmedia.com