Search code examples
spam-preventionspamassassin

How SpamAssassin defines BAYES_99 ? How to avoid it?


SpamAssassin marks my email with reason BAYES_99 , which means the email is 99% ~ 100% spam email. What is the mechanism of SpamAssassin to detect this rule (by keyword?), and how can I avoid hitting this rule?


Solution

  • BAYES_99 is a statistical component of SpamAssasin. It is using some sort/variation of Naive Bayes which has (to keep it simple) some sort of probability saying that some word/token is likely to be spam or not to be spam.

    In "math" these could be expressed like this:

    P(Class_Spam | Email)
    P(NotClass_Spam | Email)
    

    Transformations lead to e.g. this equation:

    enter image description here

    However there a lots of different representations of bayes classifiers. With different optimizations and statistical models.

    You may disable it via spamassasin configuration. This question is not well placed on stackoverflow. Superuser would be the better fit though.