Informant38

Because it is measuring probabilities, the Bayesian approach considers all the evidence in the email, both good and bad. Words that occur disproportionately rarely in spam (like "though" or "tonight" or "apparently") contribute as much to decreasing the probability as bad words like "unsubscribe" and "opt-in" do to increasing it. So an otherwise innocent email that happens to include the word "sex" is not going to get tagged as spam.....

But these numbers are not misleading, because that is the approach I'm advocating: filter each user's mail based on the spam and nonspam mail he receives. Essentially, each user should have two delete buttons, ordinary delete and delete-as-spam. Anything deleted as spam goes into the spam corpus, and everything else goes into the nonspam corpus.....

If I thought that I could keep up current rates of spam filtering, I would consider this problem solved. But it doesn't mean much to be able to filter out most present-day spam, because spam evolves. Indeed, most antispam techniques so far have been like pesticides that do nothing more than create a new, resistant strain of bugs.

Paul Graham has a plan for spam