Bengali News Classification Using Different Machine Learning and Deep Learning Algorithm

Abstract

In this modern era, Artificial Intelligence has emerged as the next data science powerhouse. The use of Machine Learning, Deep Learning, and Computer Vision algorithms in data analytics has become a popular trend since their introduction. However, applying Support Vector Machine, Naïve Bayes, Convolution Neural Network, Long Short-Term memory in different Bengali text classification tasks and study the performance of these models is yet to be explored. Hence, in this paper, we have proposed different machine learning ad deep learning based model building in order to classify 7 types of news category of Bengali newspaper data. I have compared their all-accuracy level between all of the building model SVM, Naïve Bayes, CNN, LSTM, CNN-LSTM and between all of them LSTM and CNN have achieved fairly high accuracy with the containing of a 0.5(504266) million datasets.