Vietnamese text classification using NLP techniques

Abstract

In this thesis, I have provided a solution for automated text classification of Vietnamese text using NLP techniques using 4 different machine learning models. After experimenting, it is showed that Support Vector Machine and Multilayer Perceptron models perform best and equally well with approximately 94% accuracy. Logistic Regression model performs a little worse with 92% accuracy. Multinomial Naïve Bayes performs worst of 4 models with 87% accuracy