Next Article in Journal
Influence of Cryoconcentration on Quality Attributes of Apple Juice (Malus Domestica cv. Red Fuji)
Next Article in Special Issue
Natural Brain-Inspired Intelligence for Non-Gaussian and Nonlinear Environments with Finite Memory
Previous Article in Journal
Improving Sentence Representations via Component Focusing
Previous Article in Special Issue
Fuzzy Rules to Help Predict Rains and Temperatures in a Brazilian Capital State Based on Data Collected from Satellites
Article

Targeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks

1
School of Physics and Telecommunication Engineering, Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials, South China Normal University, Guangzhou 510006, China
2
School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ 85287, USA
3
Guangdong China Construction Pulian Technology Co., Ltd, Guangzhou 510000, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Appl. Sci. 2020, 10(3), 957; https://doi.org/10.3390/app10030957
Received: 6 January 2020 / Revised: 20 January 2020 / Accepted: 21 January 2020 / Published: 2 February 2020
Targeted sentiment classification aims to predict the emotional trend of a specific goal. Currently, most methods (e.g., recurrent neural networks and convolutional neural networks combined with an attention mechanism) are not able to fully capture the semantic information of the context and they also lack a mechanism to explain the relevant syntactical constraints and long-range word dependencies. Therefore, syntactically irrelevant context words may mistakenly be recognized as clues to predict the target sentiment. To tackle these problems, this paper considers that the semantic information, syntactic information, and their interaction information are very crucial to targeted sentiment analysis, and propose an attentional-encoding-based graph convolutional network (AEGCN) model. Our proposed model is mainly composed of multi-head attention and an improved graph convolutional network built over the dependency tree of a sentence. Pre-trained BERT is applied to this task, and new state-of-art performance is achieved. Experiments on five datasets show the effectiveness of the model proposed in this paper compared with a series of the latest models. View Full-Text
Keywords: targeted sentiment classification; attentional encoding; graph convolutional network; pre-trained BERT targeted sentiment classification; attentional encoding; graph convolutional network; pre-trained BERT
Show Figures

Figure 1

MDPI and ACS Style

Xiao, L.; Hu, X.; Chen, Y.; Xue, Y.; Gu, D.; Chen, B.; Zhang, T. Targeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks. Appl. Sci. 2020, 10, 957. https://doi.org/10.3390/app10030957

AMA Style

Xiao L, Hu X, Chen Y, Xue Y, Gu D, Chen B, Zhang T. Targeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks. Applied Sciences. 2020; 10(3):957. https://doi.org/10.3390/app10030957

Chicago/Turabian Style

Xiao, Luwei, Xiaohui Hu, Yinong Chen, Yun Xue, Donghong Gu, Bingliang Chen, and Tao Zhang. 2020. "Targeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks" Applied Sciences 10, no. 3: 957. https://doi.org/10.3390/app10030957

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop