document-classifier | Web API for classifying documents according to their topic

document-classifier is a C# library. document-classifier has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub, GitLab.

This project implements an HTTP REST web service for classifying document topics, using a Naive Bayes classifier. At any given point in time, the service can receive: (1) a training document already classified with a topic; (2) a test document, to which it has to return a prediction for the topic of that document. This implementation provides persistance of the training data, and allows the system to improve dynamically with new training data. It also scales automatically to new topics, and does not store the documents itself, but the resulting bag of words. In the classification (i.e. testing) step, it takes advantage of sparsity of the input text to efficiently (and dynamically) consider only the required feature set.