|
|
New Spam Word Study
By Pete Freitag
Expert Author
Article Date: 2005-08-04
We recently analyzed the tokens (or words) in the bayesian spam filter on our mail server.
We analyzed a few different things with this data, but what what was the most interesting was the spam to ham (legitimate email) ratios. We compiled a list of 50 words with the highest spam/ham ratio.
Words like click and here don't show up as high, because they are used often in legitimate email. It does point out, however, that a word like madam is rarely found in legitimate email, and often found in spam email. Using this method we created a superior list of words found in spam email. The words are ordered from highest to lowest Spam to Ham ratio...
See the list here http://blog.activsoftware.com/entry/36/top_50_spam_words
About the Author:
Pete Freitag (http://www.petefreitag.com/) is a software engineer, and
web developer located in central new york. Pete specializes in the
HTTP protocol, web services, xml, java, and coldfusion. In 2003 Pete
published the ColdFusion MX Developers Cookbook with SAMs Publishing.
Pete owns a Firm called Foundeo (http://foundeo.com/) that specializes
in Web Consulting, and Products for Web Developers.
|
