Open Text Classification

This is a demo website to show the capability of OpenTC, which is running in the background listening to the port 3333. The website is running Django, and forward the prediction request from the web client to the OpenTC server, and forward back again the result from the server to the web client as json response.

Currently it supports Bayes, Support Vector Machine (SVM), and Convolutional Neural Network (CNN) as classifier and they were trained with all 20 newsgroups (grouped by subject similarities) from the 20newsgroup dataset:

• comp.graphics, comp.os.ms-windows.misc, comp.sys.ibm.pc.hardware, comp.sys.mac.hardware, comp.windows.x
• rec.autos, rec.motorcycles, rec.sport.baseball, rec.sport.hockey
• sci.crypt, sci.electronics, sci.med, sci.space
• misc.forsale
• talk.politics.misc, talk.politics.guns, talk.politics.mideast
• talk.religion.misc, alt.atheism, soc.religion.christian

Message to classify

If you don't know what to write for prediction, just get a random wikipedia article