Plan for Spam, Version 2

bugbear writes "I just posted a new version of the Plan for Spam Bayesian filtering algorithm. The big change is to mark tokens by context. The new version decreases spams missed by 50%, to 2.5 per 1000, even though spam has gotten harder to filter since the summer. I also talk about how spam will evolve, and what to do about it."

Comments

Slow news day?

[Koyaanisqatsi]

I just posted a new version of ...

While I recognize it's a valid project, this type of announcement is more deserving of a frontpage at Sourceforge or Freshmeat. Now if there was a huge breakthrough, we could expect to see it posted here, right?

Re:Blocking spam should be illegal.

[wheany]

What good will just responding to spam do? You have to buy everything advertised in spams. Only terrorists fail to do that.

And you could do even better by forwarding the spam to everyone on you addressbook.

Re:How is spam that big of a problem?

[AssFace]

lol

I suppose if that method works for you, then rock out with your cock out.

but for those of us that own urls and/or companies that are web facing (in that everyone out there needs to see it in order to bring in money - not just a page that your parents and your best friend visit once a month) - you need to have an email (or in many cases - many emails) that is public.
(or in my case you also have a bunch of urls that you thought were amusing)
those emails get hit by bots and then you are added to lists - not to mention that you are added to lists once you have registered a domain name.
(obviously it helps to filter out the X@domainname.com where X is not one of the valid emails for that address - many hosted companies will simply let anything through that is at that url, and spam takes advatage of that)

like someone else on here said - while your method works for you, to then wonder why it is a problem for others is naive.

In the end - I use spamassassin and it f'in rules.