In article ,
Jeff in LA wrote:
> Michael T. Davis wrote:
>
> > When such messages get directed to the Junk folder, have you been
> > identifying them as "not junk?"
>
> Somehow I'd not understood that the 'not junk'-ing of an email was
> remembered for future reference... I think this will resolve my
> problem.
To get maximum value from the spam filter, you need to train it. To do
this, if a message is spam but Eudora does not detect it, you need to
mark it as junk so Eudora will learn how to identify junk mail better.
Similarly, if a message appears in the Junk folder but is not junk, you
need to mark it as "not junk". Again, the spam filter will learn to
recognise that messages like that are not spam.
However, this a black-and-white distinction. Eudora's spam filter
actually operates in shades of grey - it scores messages on a scale of 1
to 100. If a message's score is greater than a certain value, it is
regarded as junk mail.
In my case, the value is 40. Anything over 40 is junk, anything under 40
is ok.
Now what if a good message comes in as 37? The spam filter has been very
close to calling this junk. In fact, over time, similar messages may end
up with scores over 40 unless you do something about it. (This I guess
is an aspect of the algorithm, that lots of almost identical messages
probably indicates spam.)
So it is worthwhile marking good messages whose score is above 10 or 20
as "not junk" so that Eudora learns that those types of messages are
really ok.
Similarly, some messages in Junk are only slightly over 40, meaning that
the spam filter had some doubts about whether they were spam. If they
really are spam, it is worth telling Eudora that they are spam so as to
remove any doubts.
In summary, what this means is:
1. Periodically open your Junk folder and mark all the messages as junk
(after checking that there are no false positives).
2. If any good e-mails have a score of 20 or more, mark them as "not
junk".
Using this method, I get pretty good results. According to Eudora's
statistics, I received 21638 messages last year. Of those, there were
390 messages (1.8%) not identified correctly as junk (ie, I had to mark
them as junk). There were 80 messages (0.3%) incorrectly identified as
junk. The total number of junk messages was 1545, or about 7% of my
messages.
(It would be interesting to know what success rate other people are
getting with the spam filter.)
Cheers
David
>> Stay informed about: Junk Filter Question