info-gnus-english
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: bogofilter behavior


From: Reiner Steib
Subject: Re: bogofilter behavior
Date: Tue, 03 Aug 2004 13:57:18 +0200
User-agent: Gnus/5.1006 (Gnus v5.10.6) Emacs/21.3.50 (gnu/linux)

On Tue, Aug 03 2004, Harry Putnam wrote:

> The bogofilter mail list seems to be pretty dead.  

On <URL:http://news.gmane.org/gmane.mail.bogofilter.general/> the last
messages are 3 days old.  (I didn't see any message from you on the
list.)

Note that you need to be subscribed:

,----[ http://gmane.org/info.php?group=gmane.mail.bogofilter.general ]
| Group:        gmane.mail.bogofilter.general (NNTP, HTTP)
| Status:       non-public (requires subscription to mailing list to post)
| Description:  general discussion about the bogofilter spam filter
| Url:          http://bogofilter.sourceforge.net/
`----

> In bogo_spam.in group some false positives occur and I run them back
> thru bogofilter according to my reading of the man pages, this should
> correct any misfiling that occured in bogo data base.  
>
> `bogofilter -v -Sn < MSG_NUM (a false positive file name)
                                  ^^^^^^^^^^^^^^

You meant "false negative" or you should use "-N" (if I understand
correctly)?  "false positive" means "a ham message classified as spam
by the filter".

,----[ bogofilter(1) ]
|       The  -S  option  tells   bogofilter  to  register  the  text
|       presented  on standard  input as  spam and  to undo  a prior
|       registration of the same message as non-spam.
|
|       The  -N  option  tells   bogofilter  to  register  the  text
|       presented on standard input as  non-spam and to undo a prior
|       registration of the same message as spam.
`----

You may want to read the following parts of the Gnus manual to do this
more conveniently from Gnus:

(info "(gnus)Filtering Spam Using The Spam ELisp Package")
(info "(gnus)Thwarting Email Spam")

> However some of these false hits have recurred several times and are
> very similar.  I was under the impression that the above command would
> tell bogofilter these are not spam.  It seems to have no effect.

Training only changes the ham/spam probabilities of the words (and
headers) of that message.  It is possible that reporting a false hit
once is not sufficient to change the spamicity from ham (or unsure) to
spam.

Bye, Reiner.
-- 
       ,,,
      (o o)
---ooO-(_)-Ooo--- PGP key available via WWW   http://rsteib.home.pages.de/


reply via email to

[Prev in Thread] Current Thread [Next in Thread]