On Mon, 2004-10-18 at 11:32, Mathieu Nantel wrote: > Good day list, > > As I've read a few articles on DSPAM claiming that it's better/faster/sexier > than spamassassin, I would appreciate having this list's comment on DSPAM. > I'm sure quite a few of you have tried it and might have some interesting > experiences to share. My understanding is that DSPAM relies solely on > algorithms (Bayes, CHI^2), and that complications arise when you have to > teach your users on how to train the system (which SA doesn't require as it's > based on other things aside from Bayes). > > I'm not wanting to start a church war - please be objective should you reply. > > Thanks.
I'm running it on a test system, with few (~15) users. It's been working and trained for about 4 months, and has yet to achieve better than %75 percent accuracy. One user in particular, gets about 500 Spam per month, to 3 good emails per month. In this case, DSPAM fails terribly, failing to tag ANYTHING as spam. In three months of constant training, it claims to have achieved 102% accuracy, while clearly passing everything. DSPAM has a nice user interface, but apparently requires way too much user intervention in the beginning to be very useful. YMMV -- Don
