PSCS Wiki

User Tools

Site Tools

Trace:
how_to:training_the_spam_filter

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision		Previous revision
Last revisionBoth sides next revision
how_to:training_the_spam_filter [2009/08/20 11:35] – created paulhow_to:training_the_spam_filter [2010/12/03 09:40] – paul
Line 8: Line 8:
   * Every time you receive a message which VPOP3 decides is spam, the words in that message are learnt as being words found in spam.   * Every time you receive a message which VPOP3 decides is spam, the words in that message are learnt as being words found in spam.
   * Every time you receive a message which VPOP3 decides is not spam, the words in that message are learnt as being words found in not-spam.   * Every time you receive a message which VPOP3 decides is not spam, the words in that message are learnt as being words found in not-spam.
-  * If you receive a message which is spam, which the spam filter did not detect, you can forward it to **spam@**<your domain>. The spam filter will then un-learn the words in that message as being words in not-spam, and re-learn them as being words found in spam.+  * If you receive a message which is spam, which the spam filter did not detect, you can forward it to **spam@**<your domain>. The spam filter will then un-learn the words in that message as being words in not-spam, and re-learn them as being words found in spam. (Note that although forwarding the message will alter the message slightly usually this is not significant).  
 +  * If you receive a message which is spam and view it in Webmail you can mark the message as spam from there and VPOP3 will un-learn the words as being not-spam, and re-learn them as spam.
   * If you receive a message which is not spam, but which the spam filter incorrectly detected as spam, when you release the message from the spam quarantine, the spam filter will un-learn the words as being found in spam, and re-learn them as words being found in not-spam.   * If you receive a message which is not spam, but which the spam filter incorrectly detected as spam, when you release the message from the spam quarantine, the spam filter will un-learn the words as being found in spam, and re-learn them as words being found in not-spam.
  
Line 20: Line 21:
 Note that VPOP3 will **never** automatically add addresses to the 'Blacklist'. This is because spammers often forge email addresses, so automatically adding entries to the Blacklist runs the risk of adding legitimate senders to that list. Also, it rarely is of any benefit, since spammers rarely re-use their forged addresses, so a big Blacklist just slows down the spam filtering for only minor benefit. Note that VPOP3 will **never** automatically add addresses to the 'Blacklist'. This is because spammers often forge email addresses, so automatically adding entries to the Blacklist runs the risk of adding legitimate senders to that list. Also, it rarely is of any benefit, since spammers rarely re-use their forged addresses, so a big Blacklist just slows down the spam filtering for only minor benefit.
  
 +{{tag>spamfilter whitelist blacklist bayesian filter}}
how_to/training_the_spam_filter.txt · Last modified: 2018/11/14 10:45 by 127.0.0.1

Page Tools

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki