Classification Turkish SMS with Deep Learning Tool Word2Vec

Abstract

In this study, it was aimed to develop SMS (Short Message) classification application based on deep learning. By examining messages collected from different age groups and regions, feature labels that could be effective in classification were included in the message data set. After that, the model to he used in the classification was created through Word2Vec library. With this model, new features were extracted, test messages were classified and analyzed, and the results were discussed.