Reputation: 669
I am trying to build spam filtering application using text categorization. From where should I start learning the algorithms? Which algorithm should I implement first? Anyone can suggest any good material?
Upvotes: 0
Views: 1391
Reputation: 191
The easiest one to start with is Naive Bayes.
http://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-classification-1.html
Upvotes: 3
Reputation: 4315
I found this article [PDF] that gives quite a good overview of available machine learning techniques and their performance for spam filtering.
Here you can find more information on the subject as well as training data!
I must say that there are volumes of material online, simple google search for "spam filtering machine learning techniques" is enough.
Upvotes: 1