Ending Spam:Bayesian Content Filtering and the Art of Statistical Language Classification
The title makes this sound like ultra-heavy geek territory. A review
of chapter titles seemed to confirm that impression: "Fifth Order
Markovian Discrimination" - Oh, my!.. I visualized page after page of
unintelligible mathematical symbols swimming past my glazed over
eyes. I was also having trouble raising my enthusiasm for other
reasons: I've read a number of books and articles on spam recently
and the thought of another on the same theme was just not ringing any
Fearing the worst, I took a deep breath, dove in and was
instantly surprised. The first
part of the book was genuinely delightful: a well written history
of the origins of spam. It then segues to the techniques that have
been used to identify spam, and moves to the current methods.
Markovian Discrimination turned out to be a technique I've used in
other programming efforts, and the author explains it and everything
else in simple and entertaining language. There's nothing here
that any competent programmer can't grasp.
I'm a little hesitant to call this book entertaining, although it
actually is. I only hesitate because saying that might give the impression
that there is more fluff than substance, and that's not the case.
There is a lot of substance here, both in theory and in practical
advice. And although the subject is definitely spam, some of the
techniques and methods discussed here apply to other programming
challenges as well.
Overall, worth reading, even by non-programmers wanting to understand
more about what current anti-spam efforts are all about.
- Jonathan A. Zdziarski
- No Starch Press
Got something to add? Send me email.
Increase ad revenue 50-250% with Ezoic
More Articles by Tony Lawrence
Find me on Google+
© 2011-04-28 Tony Lawrence