Journal
COMPUTER JOURNAL
Volume 64, Issue 7, Pages 1069-1079Publisher
OXFORD UNIV PRESS
DOI: 10.1093/comjnl/bxab104
Keywords
aspect sentiment classification; graph convolution networks; opinion mining; multi-head attention mechanism
Categories
Funding
- China Key Research Program [2016YFB1000905]
- Natural Science Foundation of China [61876046, 61573270]
- Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent Processing
- Guangxi High Institutions Program of Introducing 100 HighLevel Overseas Talents
- Guangxi `Bagui' Teams for Innovation and Research
- Marsden Fund of New Zealand [MAU1721]
- Project of Guangxi Science and Technology [GuiKeAD17195062, GuiKeAD20159041]
- Research Fund of Guangxi Key Lab of Multisource Information Mining and Security [18-A-01-01, 20-A-01-01]
Ask authors/readers for more resources
Aspect sentiment classification is an important research topic, and this paper introduces a network framework to improve the classification by learning representation from a concurrence-words relation graph. Experimental results show a significant improvement in prediction performance across five benchmark datasets.
Aspect sentiment classification is an important research topic in natural language processing and computational linguistics, assisting in automatically review analysis and emotional tendency judgement. Different from extant methods that focus on text sequence representations, this paper presents a network framework to learn representation from concurrence-words relation graph (LRCWG), so as to improve the Macro-F1 and accuracy. The LRCWG first employs the multi-head attention mechanism to capture the sentiment representation from the sentences which can learn the importance of text sequence representation. And then, it leverages the priori sentiment dictionary information to construct the concurrence relations of sentiment words with Graph Convolution Network (GCN). This assists in that the learnt context representation can keep both the semantics integrity and the features of sentiment concurrence-words relations. The designed algorithm is experimentally evaluated with all the five benchmark datasets and demonstrated that the proposed aspect sentiment classification can significantly improve the prediction performance of learning task.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available