Sentiment Analysis of Weibo Comments Based on Deep Neural Network
Fang Hao Wan · 2019
With the rapid development of network information technology, social media has become a new information dissemination platform, and has the characteristics of rapid dissemination and wide audience. This paper proposes a micro-blog commentary sentiment analysis method based on deep neural network. By constructing multi-level pooling layer and convolution layer, the network complexity is increased, and then the data features can be effectively extracted, the sentiment analysis accuracy rate can be improved, and the network can be avoided. Locally optimal. Firstly, the microblog commentary is preprocessed, then the word2vec algorithm is used for text representation, and the feature matrix is input into the convolutional neural network to extract the key features in the text. Finally, the softmax logistic regression network is used to classify the features and obtain the sentiment analysis results. Through experimental verification, the accuracy of this method is significantly improved compared with the traditional machine learning method.