Knowledge-Guided Heterogeneous Graph Convolutional Network for Aspect-Based Sentiment Analysis

被引:0
|
作者
Song, Xiangxiang [1 ]
Ling, Guang [1 ]
Tu, Wenhui [1 ]
Chen, Yu [1 ]
机构
[1] Wuhan Univ Technol, Sch Sci, Wuhan 430070, Peoples R China
关键词
ABSA; HGCN; knowledge graph; feature fusion; LSTM; BERT;
D O I
10.3390/electronics13030517
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The purpose of aspect-based sentiment analysis (ABSA) is to determine the sentiment polarity of aspects in a given sentence. Most historical works on sentiment analysis used complex and inefficient methods to integrate external knowledge. Furthermore, they fell short of completely utilizing BERT's potential because when trying to generate word embeddings, they merely averaged the BERT subword vectors. To overcome these limitations, we propose a knowledge-guided heterogeneous graph convolutional network for aspect-based sentiment analysis (KHGCN). Specifically, we consider merging subword vectors utilizing a dynamic weight mechanism in the BERT embedding layer. Additionally, heterogeneous graphs are constructed to fuse different feature associations between words, and graph convolutional networks are utilized to identify context-specific syntactic features. Furthermore, by embedding a knowledge graph, the model can learn additional features from sources other than the corpus. Based on this knowledge, it is consequently possible to obtain more knowledge representation for a particular aspect by utilizing the attention mechanism. Last but not least, semantic features, syntactic features, and knowledge are dynamically combined using feature fusion. Experiments on three public datasets demonstrate that our model achieves accuracy rates of 80.87%, 85.42%, and 91.07%, which is an improvement of more than 2% compared to other benchmark models based on HGCNs and BERT.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis
    Zhang, Zheng
    Zhou, Zili
    Wang, Yanna
    [J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 4916 - 4925
  • [22] Affective Knowledge Augmented Interactive Graph Convolutional Network for Chinese-Oriented Aspect-Based Sentiment Analysis
    Yang, Qian
    Kadeer, Zaokere
    Gu, Wenxia
    Sun, Weiwei
    Wumaier, Aishan
    [J]. IEEE ACCESS, 2022, 10 : 130686 - 130698
  • [23] A novel weight-oriented graph convolutional network for aspect-based sentiment analysis
    Bengong Yu
    Shuwen Zhang
    [J]. The Journal of Supercomputing, 2023, 79 : 947 - 972
  • [24] Dynamic and Multi-Channel Graph Convolutional Network for Aspect-Based Sentiment Analysis
    Pang, Shiguan
    Xue, Yun
    Yang, Zehao
    Huang, Weihao
    Feng, Jinhui
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 2627 - 2636
  • [25] A novel weight-oriented graph convolutional network for aspect-based sentiment analysis
    Yu, Bengong
    Zhang, Shuwen
    [J]. JOURNAL OF SUPERCOMPUTING, 2023, 79 (01): : 947 - 972
  • [26] Local Dependency-Enhanced Graph Convolutional Network for Aspect-Based Sentiment Analysis
    Wu, Fei
    Li, Xinfu
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (17):
  • [27] Multi-channel Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis
    Han, Hu
    Fan, Yating
    Xu, Xuefeng
    [J]. Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2024, 46 (03): : 1022 - 1032
  • [28] Aspect-gated graph convolutional networks for aspect-based sentiment analysis
    Lu, Qiang
    Zhu, Zhenfang
    Zhang, Guangyuan
    Kang, Shiyong
    Liu, Peiyu
    [J]. APPLIED INTELLIGENCE, 2021, 51 (07) : 4408 - 4419
  • [29] Aspect-gated graph convolutional networks for aspect-based sentiment analysis
    Qiang Lu
    Zhenfang Zhu
    Guangyuan Zhang
    Shiyong Kang
    Peiyu Liu
    [J]. Applied Intelligence, 2021, 51 : 4408 - 4419
  • [30] Fusing Syntax and Semantics-Based Graph Convolutional Network for Aspect-Based Sentiment Analysis
    Feng, Jinhui
    Cai, Shaohua
    Li, Kuntao
    Chen, Yifan
    Cai, Qianhua
    Zhao, Hongya
    [J]. INTERNATIONAL JOURNAL OF DATA WAREHOUSING AND MINING, 2023, 19 (01)