Naiban is fully functioning standalone application and an Avalon/Keel classification service:
Naive Bayes learning classifiers have recently gained popularity in their application to the spam vs. ham problem. By training only on misclassified data, these classifiers provide a very efficient and accurate method of classifing text.
Naiban provides a learning classifier service to the Avalon/Keel framework, and comes complete with two text classifiers and a simple numeric classifier. It is easily extendable, and provides two persistance mechanisms for storing trained data.