What do I need to run the GMS Anti-Spam Bayesian Filter?
GMS Anti-Spam includes a client side Bayesian filter. Bayesian based filters calculate the probability of a message being spam based on the contents of that message. Unlike simple content-based filters, Bayesian filtering learns from both good and bad messages, resulting in a very efficient, self learning, anti-spam system that will return
very few false positives.
To prime the filter you should ideally start with a large number of messages that you have already classified as bad, and another which you have classified as good. These should then be fed into the Bayesian filter to prime it with content. The filter will look at both good and bad
messages, analyzing both to calculate the probability of various characteristics appearing in messages.
The Bayesian filter included in GMS Webmail is designed in such a way that when it is enabled it should greatly reduce the amount of spam arriving in your mailbox.
The option to use Bayesian filters is only available to users if that option has been enabled by the system administrator.
The files required to run the filter must be installed in the gordanobin directory on the mail server. Once the files are in place the Bayesian filter option will automatically become enabled and available for use. The required files can be downloaded from the Gordano website http://www.gordano.com, please be sure to select the correct files for your operating system.
Full details and instructions on how best to use the Bayesian filter can be found in the GMS User Guide.
Keywords:as anti-spam antispam anti spam bayesian filter