科研之友
微信
新浪微博
Facebook
分享链接
摘要
Identifying sentiment polarity of a document is a building block of sentiment analysis and natural language processing tasks, and it aims to automate the prediction of a user's sentiment orientation in the document about a product, on assumption that the document expresses a sentiment on a single product. In general, supervised machine learning models like support vector machine and recently fast-growing deep neural networks method have been extensively used as a sentiment learning approach. Although some neural network-based models learn text features without feature engineering, most of them only focus on extracting semantic representations from single words and rarely consider the contexts attributed to the correlation between words and sentences. In this paper, we propose a novel neural network model to capture the context information from texts. Our model builds a hybrid neural network model using convolutional neural networks and long short-term memory for word context extraction and document representation, respectively. On this basis, user's and product's information can be incorporated into the model. The experimental results show the competitive performance of our model, compared to all state-of-the-art methods.
