Difference between revisions of "Bayes Analysis"

From Roaring Penguin
Jump to: navigation, search
Line 4: Line 4:
  
 
In terms of user input to train and maintain the system to adapt to the
 
In terms of user input to train and maintain the system to adapt to the
actual spam and non-spam your organization receives there two areas to
+
actual spam and non-spam your organization receives there are two areas to
 
be aware of. The first is mail actually trapped in one of the
 
be aware of. The first is mail actually trapped in one of the
 
quarantines. Mail accepted/released for delivery will also be voted as
 
quarantines. Mail accepted/released for delivery will also be voted as
Line 10: Line 10:
 
voted as spam. Note that messages rejected from the pending quarantine
 
voted as spam. Note that messages rejected from the pending quarantine
 
will not be immediately discarded but are rather placed in the spam
 
will not be immediately discarded but are rather placed in the spam
quarantine to allow a possible second to reset their disposition.  Any
+
quarantine to allow a second chance to reset their disposition.  Any
 
messages that are just left in either the pending or spam quarantines
 
messages that are just left in either the pending or spam quarantines
are expire out after the set durations are not voted.
+
are expire out after the set durations and are not voted.
  
The second area is the voting links that can be placed at the end of
+
The second area is the voting links that can be placed at the end of incoming message. This is controlled by the  setting "S-2500
any incoming message. This is controlled by the  setting "S-2500
 
 
Add links to messages to train Bayesian analyzer" on the
 
Add links to messages to train Bayesian analyzer" on the
Preferences->Quarantine Settings of the webui. Upon installation this
+
Preferences->Quarantine Settings page of the webui. Upon installation this
 
is set to Inline by default which means the voting links will appear on
 
is set to Inline by default which means the voting links will appear on
 
incoming messages. Clicking on a link will allow you to do the Bayes
 
incoming messages. Clicking on a link will allow you to do the Bayes

Revision as of 10:55, 11 March 2016

Bayes analysis is the learning system built into CanIt. There is a brief description of the system in the User Guide in section "9.1 Introduction to Bayesian Filtering".

In terms of user input to train and maintain the system to adapt to the actual spam and non-spam your organization receives there are two areas to be aware of. The first is mail actually trapped in one of the quarantines. Mail accepted/released for delivery will also be voted as non-spam for the purpose of Bayes while those rejected will also be voted as spam. Note that messages rejected from the pending quarantine will not be immediately discarded but are rather placed in the spam quarantine to allow a second chance to reset their disposition. Any messages that are just left in either the pending or spam quarantines are expire out after the set durations and are not voted.

The second area is the voting links that can be placed at the end of incoming message. This is controlled by the setting "S-2500 Add links to messages to train Bayesian analyzer" on the Preferences->Quarantine Settings page of the webui. Upon installation this is set to Inline by default which means the voting links will appear on incoming messages. Clicking on a link will allow you to do the Bayes voting without having to long into the CanIt webui.

One point worth emphasis is that care should be taken in voting messages. If messages are incorrectly marked as spam or non-spam this can "poison" the Bayes database and degrade the effectiveness of the analyzer. You are better to delete or allow a message to expire than voting it incorrectly.

For more specific detail consult either the User Guide or the Administrators Guide documentation.