Multi-channel Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis

被引:1
作者
Han, Hu [1 ]
Fan, Yating [1 ]
Xu, Xuefeng [1 ]
机构
[1] Lanzhou Jiaotong Univ, Sch Elect & Informat Engn, Lanzhou 730070, Peoples R China
基金
中国国家自然科学基金;
关键词
Aspect-based sentiment analysis; Graph Convolutional Network(GCN); Affective knowledge; Dependency relation embedded; Multi-head attention;
D O I
10.11999/JEIT230353
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In traditional single-channel-based feature extraction approaches, features are captured solely based on dependency, while semantic similarity and dependency types between words are ignored. Although some success has been achieved through the graph convolutional network-based approach for sentiment analysis, aggregating both semantic information and syntactic structure features remains challenging, and the gradual loss of semantic features throughout the training process affects the final sentiment classification effect. To prevent the model from misinterpreting relevant sentiment words due to the absence of prior knowledge, the inclusion of external knowledge is recommended to enrich the text. Presently, how to utilize Graph Neural Networks(GNN) to fuse syntactic and semantic features still deserves further research. A multi-channel enhanced graph convolutional network model is proposed in this paper to address the above issues. First, graph convolution operations on syntactic graphs enhanced with sentiment knowledge and dependency types are performed to obtain two syntax-based representations, which are fused with the semantic representations learned through multi-head attention and graph convolution, so that the multi-channel features can be learned complementarily. It is observed from the experimental results that both the accuracy and macro F1 of our model surpass those of the benchmark model on five publicly available datasets. These findings indicate the importance of dependency types and affective knowledge to enhance syntactic graphs and highlight the effectiveness of combining semantic information with syntactic structure.
引用
收藏
页码:1022 / 1032
页数:11
相关论文
共 26 条
[1]   SenticNet 6: Ensemble Application of Symbolic and Subsymbolic AI for Sentiment Analysis [J].
Cambria, Erik ;
Li, Yang ;
Xing, Frank Z. ;
Poria, Soujanya ;
Kwok, Kenneth .
CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, :105-114
[2]   Learning from word semantics to sentence syntax by graph convolutional networks for aspect-based sentiment analysis [J].
Dai, Anan ;
Hu, Xiaohui ;
Nie, Jianyun ;
Chen, Jinpeng .
INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS, 2022, 14 (01) :17-26
[3]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[4]  
Dong L, 2014, PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, P49
[5]  
Huang BX, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P5469
[6]   Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks [J].
Liang, Bin ;
Su, Hang ;
Gui, Lin ;
Cambria, Erik ;
Xu, Ruifeng .
KNOWLEDGE-BASED SYSTEMS, 2022, 235
[7]  
Ma DH, 2017, PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P4068
[8]  
Zhang M, 2020, PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), P3540
[9]   Contextual Graph Attention Network for Aspect-Level Sentiment Classification [J].
Miao, Yuqing ;
Luo, Ronghai ;
Zhu, Lin ;
Liu, Tonglai ;
Zhang, Wanzhen ;
Cai, Guoyong ;
Zhou, Ming .
MATHEMATICS, 2022, 10 (14)
[10]  
Pennington J., 2014, P 2014 C EMP METH NA, P1532, DOI [DOI 10.3115/V1/D14-1162, 10.3115/v1/D14-1162]