Affective-Knowledge-Enhanced Graph Convolutional Networks for Aspect-Based Sentiment Analysis with Multi-Head Attention

被引:4
|
作者
Cui, Xiaodong [1 ,2 ]
Tao, Wenbiao [1 ,2 ]
Cui, Xiaohui [1 ,3 ]
机构
[1] Yunnan Univ, Engn Res Ctr Cyberspace, Kunming 650504, Peoples R China
[2] Yunnan Univ, Pilot Sch Software, Kunming 650504, Peoples R China
[3] Wuhan Univ, Sch Cyber Sci Additionally, Enginning, Wuhan 430072, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 07期
关键词
graph convolutional network; aspect-based sentiment analysis; multi-head attention; ONTOSENTICNET;
D O I
10.3390/app13074458
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Aspect-based sentiment analysis (ABSA) is a task in natural language processing (NLP) that involves predicting the sentiment polarity towards a specific aspect in text. Graph neural networks (GNNs) have been shown to be effective tools for sentiment analysis tasks, but current research often overlooks affective information in the text, leading to irrelevant information being learned for specific aspects. To address this issue, we propose a novel GNN model, MHAKE-GCN, which is based on the graph convolutional neural network (GCN) and multi-head attention (MHA). Our model incorporates external sentiment knowledge into the GCN and fully extracts semantic and syntactic information from a sentence using MHA. By adding weights to sentiment words associated with aspect words, our model can better learn sentiment expressions related to specific aspects. Our model was evaluated on four publicly benchmark datasets and compared against twelve other methods. The results of the experiments demonstrate the effectiveness of the proposed model for the task of aspect-based sentiment analysis.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Attention-Enhanced Graph Convolutional Networks for Aspect-Based Sentiment Classification with Multi-Head Attention
    Xu, Guangtao
    Liu, Peiyu
    Zhu, Zhenfang
    Liu, Jie
    Xu, Fuyong
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (08):
  • [2] Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks
    Liang, Bin
    Su, Hang
    Gui, Lin
    Cambria, Erik
    Xu, Ruifeng
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 235
  • [3] Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification
    Luwei Xiao
    Xiaohui Hu
    Yinong Chen
    Yun Xue
    Bingliang Chen
    Donghong Gu
    Bixia Tang
    [J]. Multimedia Tools and Applications, 2022, 81 : 19051 - 19070
  • [4] Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification
    Xiao, Luwei
    Hu, Xiaohui
    Chen, Yinong
    Xue, Yun
    Chen, Bingliang
    Gu, Donghong
    Tang, Bixia
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (14) : 19051 - 19070
  • [5] Multi-Head Self-Attention Transformation Networks for Aspect-Based Sentiment Analysis
    Lin, Yuming
    Wang, Chaoqiang
    Song, Hao
    Li, You
    [J]. IEEE ACCESS, 2021, 9 : 8762 - 8770
  • [6] Deep Multi-Head Attention Network for Aspect-Based Sentiment Analysis
    Yan, Danfeng
    Chen, Jiyuan
    Cui, Jianfei
    Shan, Ao
    Shi, Wenting
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2019, : 695 - 700
  • [7] Aspect-based sentiment analysis with component focusing multi-head co-attention networks
    Cheng, Li-Chen
    Chen, Yen-Liang
    Liao, Yuan-Yu
    [J]. NEUROCOMPUTING, 2022, 489 : 9 - 17
  • [8] Memory network with hierarchical multi-head attention for aspect-based sentiment analysis
    Yuzhong Chen
    Tianhao Zhuang
    Kun Guo
    [J]. Applied Intelligence, 2021, 51 : 4287 - 4304
  • [9] Memory network with hierarchical multi-head attention for aspect-based sentiment analysis
    Chen, Yuzhong
    Zhuang, Tianhao
    Guo, Kun
    [J]. APPLIED INTELLIGENCE, 2021, 51 (07) : 4287 - 4304
  • [10] Graph convolutional networks with hierarchical multi-head attention for aspect-level sentiment classification
    Li, Xiaowen
    Lu, Ran
    Liu, Peiyu
    Zhu, Zhenfang
    [J]. JOURNAL OF SUPERCOMPUTING, 2022, 78 (13): : 14846 - 14865