Application of Convolutional Neural Network (Cnn)in Microblog Text Classification

Abstract

At present, Weibo has become the main platform of lyric fermentation in China. On this platform, Chinese people can discuss many major events, so it is very necessary to monitor the grievances on Weibo in time. This paper aims to classify and monitor Weibo public opinion through Convolutional Neural Network (CNN). Firstly, the data is cleaned up and a vocabulary is built. Then the model of the convolutional neural network is built, including the embedding layer, the convolution layer, the pooling layer and the fully connected layer. Finally, the data is predicted and classified by the Softmax function. The experimental results show that the model can effectively classify and predict the Weibo public opinion, which is a certain improvement compared with the traditional machine learning algorithm.