According to several people on StackOverflow Bayesian filtering is better than Neural Networks for detecting spam.

According to the literature I've read that shouldn't be the case. Please explain!

  • 9
    $\begingroup$ Could you provide links and background information please? $\endgroup$ – Aaron Sterling Nov 7 '11 at 18:10
  • 4
    $\begingroup$ This is really out of scope for this site. $\endgroup$ – Suresh Venkat Jun 29 '12 at 6:13
  • $\begingroup$ why is it out of scope? its about machine-learning and ai.artificial-intel. too applied? $\endgroup$ – vzn Jun 30 '12 at 14:55
  • $\begingroup$ re the Q unless there is some theoretical proof of deficiency, there is no theoretical reason to prefer one approach or another. as for implementations, it may be that a community might reach a consensus on performance, but that cannot anticipate future improvements to the different approaches. as for "better", that must be carefully defined. is one faster than the other? easier to implement? more accurate? etc? $\endgroup$ – vzn Jun 30 '12 at 14:57

It would be interesting to know what litterature you have read.

As far as I know, Bayesian filters were working very well. That's because the learning is based on the words used, and a Bayesian filter is quick to understand that an email containt "Viagra" is likely spam.

But spammers are not so stupid, and they quickly introduced mispelled word. "VI4GRA" has never been seen in any spam before. In a word: it's easy to work around a Bayesian filter.

Neural Networks can be good at classifying. But there are two difficulties: the choice of measures ; the training data.

| cite | improve this answer | |
  • 2
    $\begingroup$ VI4GRAs are pre-processed. They aren't any problem for either of the methods. $\endgroup$ – Pratik Deoghare Dec 9 '11 at 11:46

Bayesian filtering is not better than Neural Networks for classifying spam because Bayesian filtering cannot learn a spammer's tactics change but NNs can.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.