Attention-based Hierarchical LSTM Model for Document Sentiment Classification

Document sentiment classification is a fundamental task in data mining, contains extensive underlying commercial value. With the development of deep learning, we can extract features in an automatic way, instead of design it by oneself. Which can help us use semantic information to classify the document in a better way. Base that, in this paper, we present a hierarchical network structure according to the structure in real document. Based on LSTM to encode semantic information; then combine with attention mechanism to improve the accuracy of classification. And last, conduct experiment on two dataset, analyse the accuracy result of different model, and study some tricks in parameter selection.