Tony Godshall wrote: > So I switched to CRM114's mailfilter. > But given SA's framework-of-methods methodology perhaps a > better approach would have been to integrate the better > learning filter into SA.
That is something they should have done in the first place. On the other
hand one thing I do like about SA's bayes implementation is that it isn't
binary. All other filters that have implemented bayesian classification in
some form or another only spew 2, maybe 3 results. Spam, ham and sometimes
"unsure". I really don't like that simplistic view of how the classifier
works and do like being able to score 80% different than 90% different than 100%.
--
Steve C. Lamb | I'm your priest, I'm your shrink, I'm your
PGP Key: 8B6E99C5 | main connection to the switchboard of souls.
-------------------------------+---------------------------------------------
signature.asc
Description: OpenPGP digital signature
