Bayesian spam filters can take one group of legitimate e-mail and another group of spam and compare values and data of each. The definition of legitimate e-mail that it creates at end of this comparison session is what it uses going forward to scan your inbox for spam.

FYI Bayesian spam filters are named after Thomas Bayes an 18 century cleric who created something known as Bayes Theorem. In summary Bayes Theorem is as follows: .."in statistical inference to update estimates of probability that different hypotheses are true, based on observations and a knowledge of how likely those observations are, given each hypothesis." In plain English it looks for obvious repeating patterns to form an "opinion" on something. In spam filter terms that "opinion" becomes a rule which keeps you spam free (or pretty close :-)

For average email user it's an annoyance. But for Internet marketer it represents a serious threat. If you're sending ezines, autoresponder messages or solo ads as a means of building your business, then there's every chance that between 10% and 50% of your recipients never get your email.

It's SP*M blockers you see.

More and more email users have installed SP*M blockers to prevent all thrash from ever reaching their inbox. Likewise, an ever-increasing number of ISPs use similar technology to protect their users.

This represents a serious challenge to legitimite marketer who's sending legitimite emails to legitimite opt-in recipients.

It's gotten to point where I can't even spell word SP*M in this article for fear it never reaches you. I should also avoid words like FR*E or M*NEY or OPP*RTUNITY or even something apparently harmless like CLICK BEL*W!!

In fact, there's so many things that will clock up points on SP*M blocker's index, that it's getting near impossible for us to write anything in our emails. (If you're interested, you can see an extensive list of kind of stuff that will earn you SP*MMER points at http://spamassassin.org ests.html).

So what can you do to get around this problem?

Simple. You've got to determine whether emails you send out are going to pass SP*M blockers criteria or not.