Talk:DSPAM

From Wikipedia, the free encyclopedia
Jump to: navigation, search
WikiProject Software / Computing   
WikiProject icon This article is within the scope of WikiProject Software, a collaborative effort to improve the coverage of software on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
 ???  This article has not yet received a rating on the project's quality scale.
 ???  This article has not yet received a rating on the project's importance scale.
Taskforce icon
This article is supported by WikiProject Computing.
 

Untitled discussion[edit]

dspam is like spamassasin but it's easier to configure and so it's more scalable so it's worth including it in wikipedia 00 tux(my point of views(for npov), howto customise a signature) | talk 21:18, 8 April 2007 (UTC)

Please read the notability guideline for how to establish notability on Wikipedia. -- intgr 21:21, 8 April 2007 (UTC)
i didn't understand what was notability...sorry(i read too much quickelu and thought it wasn't worth inclding because it wasn't part of the following categories:Biographies, Books, Companies, Fiction, Music, Neologisms, Numbers, Web content.) 00 tux(my point of views(for npov), howto customise a signature) | talk 21:31, 8 April 2007 (UTC)
dspam is totally notably notable. It's one of the premiere spam filters and is known for being several orders of magnitude more accurate than spamassasin while using significantly fewer resources. I've got a 99.935% spam identification rate with it over the past two years, so with about 800 spam per day, I'm getting at most 2 or 3 a month. I'm distrustful of the TREC 2005 paper, as it is contrary to my experience in the field with regards to spamassasin and dspam. The best I've ever gotten with spamassasin is about 95% accuracy. But the initial comment is incorrect--dspam is quite a bit more difficult to configure than spamassasin. But it is so worth the effort. --petrockette | talk 07:09, 1 February 2008 (UTC)

Is it possible you are confusing the TREC 2005 paper with the original study by Cormack? The TREC evaluation used four independent datasets, and the DSPAM configuration was vetted by Zdziarski. Furthermore, SpamAssassin result isn't so good, either, especially in its default configuration. To my knowledge, Zdziarski has not challenged the TREC results. —Preceding unsigned comment added by Gvcormac (talkcontribs) 00:32, 18 August 2009 (UTC)

Issues with this article[edit]

I've removed the three tags from this article. If anyone thinks this article still has problems (that they can't fix), please re-add the tags and also describe the problem here so that the next person will know what to fix in order to remove the reason for the tags being there. Gronky 11:51, 11 April 2007 (UTC)