一种基于深度学习的中文微博情感分析融合模型

With the continuous development of network information technology, text mining and processing are gradually being carried out by computers, and sentiment analysis is such a technology. As a natural language processing method, sentiment analysis can effectively analyze the subjective intentions contained in text information, and has a wide range of applications in product satisfaction surveys, Weibo attitude discrimination, etc. This paper firstly sorts out the previous work in this area, and proposes an integrated deep learning model for the problem of insufficient feature extraction in traditional deep learning. The model first extracts long-distance temporal features of text through a bidirectional long short-term memory network (Bilstm), and then use it as input to extract spatial features by using convolutional neural network (CNN).Further, a two-layer attention structure is used to extract the temporal features of the original text. Finally, the features extracted from these two parts are spliced and sent to the fully connected layer, and then classified. The experimental results show that the accuracy and F1 value of the model proposed in this paper are improved compared with the traditional model alone and some hybrid model.It proves the effectiveness of the model proposed in this paper..