 | This article has multiple issues. Please helpimprove it or discuss these issues on thetalk page.(Learn how and when to remove these messages) (Learn how and when to remove this message)
|
| SpamBayes | |
|---|---|
| Original author | Tim Peters |
| Initial release | September 2002 |
| Stable release | 1.0.4 / March 2005 |
| Preview release | 1.1a6 / December 6, 2008 (2008-12-06)[1] |
| Written in | Python |
| Platform | Cross-platform |
| Available in | English only |
| Type | E-mail filtering |
| License | PSFL |
| Website | spambayes.sourceforge.net |
SpamBayes is aBayesianspam filter written inPython which uses techniques laid out byPaul Graham in his essay "A Plan for Spam". It has subsequently been improved byGary Robinson andTim Peters, among others.[2]
The most notable difference between a conventional Bayesian filter and the filter used by SpamBayes is that there are three classifications rather than two: spam, non-spam (calledham in SpamBayes), and unsure. The user trains a message as being either ham or spam; when filtering a message, the spam filters generate one score for ham and another for spam.
If the spam score is high and the ham score is low, the message will be classified as spam.If the spam score is low and the ham score is high, the message will be classified as ham.If the scores are both high or both low, the message will be classified as unsure.
This approach leads to a low number offalse positives andfalse negatives, but it may result in a number of unsures which need a human decision.
Some work has gone into applying SpamBayes tofilter internet content via aproxy web server.[3][4][5]
