Neural networks for email spam detection

Question

Let's say you have access to an email account with the history of received emails from the last years (~10k emails) classified into 2 groups

• genuine email
• spam

How would you approach the task of creating a neural network solution that could be used for spam detection - basically classifying any email either as spam or not spam?

Let's assume that the email fetching is already in place and we need to focus on classification part only.

The main points which I would hope to get answered would be:

1. Which parameters to choose as the input for the NN, and why?
2. What structure of the NN would most likely work best for such task?

Also any resource recommendations, or existing implementations (preferably in C#) are more than welcome

Thank you

EDIT

• I am set on using neural networks as the main aspect on the project is to test how the NN approach would work for spam detection
• Also it is a "toy problem" simply to explore subject on neural networks and spam

Answer 1

If you insist on NNs... I would calculate some features for every email

Both Character-Based, Word-based, and Vocabulary features (About 97 as I count these):

1. Total no of characters (C)
2. Total no of alpha chars / C Ratio of alpha chars
3. Total no of digit chars / C
4. Total no of whitespace chars/C
5. Frequency of each letter / C (36 letters of the keyboard – A-Z, 0-9)
6. Frequency of special chars (10 chars: *, _ ,+,=,%,$,@,ـ , \,/ )
7. Total no of words (M)
8. Total no of short words/M Two letters or less
9. Total no of chars in words/C
10. Average word length
11. Avg. sentence length in chars
12. Avg. sentence length in words
13. Word length freq. distribution/M Ratio of words of length n, n between 1 and 15
14. Type Token Ratio No. Of unique Words/ M
15. Hapax Legomena Freq. of once-occurring words
16. Hapax Dislegomena Freq. of twice-occurring words
17. Yule’s K measure
18. Simpson’s D measure
19. Sichel’s S measure
20. Brunet’s W measure
21. Honore’s R measure
22. Frequency of punctuation 18 punctuation chars: . ، ; ? ! : ( ) – “ « » < > [ ] { }

You could also add some more features based on the formatting: colors, fonts, sizes, ... used.

Most of these measures can be found online, in papers, or even Wikipedia (they're all simple calculations, probably based on the other features).

So with about 100 features, you need 100 inputs, some number of nodes in a hidden layer, and one output node.

The inputs would need to be normalized according to your current pre-classified corpus.

I'd split it into two groups, use one as a training group, and the other as a testing group, never mixing them. Maybe at a 50/50 ratio of train/test groups with similar spam/nonspam ratios.

Answer 2

Are you set on doing it with a Neural Network? It sounds like you're set up pretty well to use Bayesian classification, which is outlined well in a couple of essays by Paul Graham:

• A Plan for Spam
• Better Bayesian Filtering

The classified history you have access to would make very strong corpora to feed to a Bayesian algorithm, you'd probably end up with quite an effective result.