Attention-based Hierarchical LSTM Model for Document Sentiment Classification

2018 2nd International Conference on Artificial Intelligence Applications and Technologies

计算机科学

Wang, Bo^1 ; Fan, Binwen^1

Harbin Institute of Technology, Shenzhen, Shenzhen, China^1

关键词: Accuracy of classifications;    Attention mechanisms;    Document sentiment classification;    Hierarchical network structure;    Parameter selection;    Semantic information;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/435/1/012051/pdf
DOI  :  10.1088/1757-899X/435/1/012051

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

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.