期刊
NEUROCOMPUTING
卷 275, 期 -, 页码 1407-1415出版社
ELSEVIER
DOI: 10.1016/j.neucom.2017.09.080
关键词
Textual sentiment analysis; Word embedding; Lexicon embedding; Attention mechanism; Cross-modality consistent regression
资金
- Natural Science Foundation of China [61702066]
- Scientific and Technological Research Program of Chongqing Municipal Education Commission [KJ1704080]
- Chongqing Research Program of Basic Research and Frontier Technology [cstc2017jcyjAX0256]
Word embeddings and CNN (convolutional neural networks) architecture are crucial ingredients of sentiment analysis. However, sentiment and lexicon embeddings are rarely used and CNN is incompetent to capture global features of sentence. To this end, semantic embeddings, sentiment embeddings and lexicon embeddings are applied for texts encoding, and three different attentions including attention vector, LSTM (long short term memory) attention and attentive pooling are integrated with CNN model in this paper. Additionally, a word and its context are explored to disambiguate the meaning of the word for rich input representation. To improve the performance of three different attention CNN models, CCR (cross-modality consistent regression) and transfer learning are presented. It is worth noticing that CCR and transfer learning are used in textual sentiment analysis for the first time. Finally, some experiments on two different datasets demonstrate that the proposed attention CNN models achieve the best or the next-best results against the existing state-of-the-art models. (c) 2017 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据