An Analytical Survey on Text Classification via Deep Learning

Text classification is the process of assigning a text to one or more classes or categories. As one of the key issues in natural language processing, text classification recently has received a lot of attention from the researchers and different techniques have been used for this purpose. In this paper, we have investigated deep learning based text classification and defined the process while introducing and examining its different models. Finally, we have compared some of the most important models of deep learning based text classification on topic classification and sentiment analysis for two English datasets. The results show that the average accuracy of deep learning based text classification is 0.89 for sentiment analysis and is 0.83 for topic classification