Aspect-level sentiment analysis for based on joint aspect and position hierarchy attention mechanism network

被引:4
|
作者
Shao, Dangguo [1 ,2 ]
An, Qing [1 ]
Huang, Kun [1 ]
Xiang, Yan [1 ,2 ]
Ma, Lei [1 ,2 ]
Guo, Junjun [1 ,2 ]
Yin, Runda [1 ]
机构
[1] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming, Yunnan, Peoples R China
[2] Kunming Univ Sci & Technol, Yunnan Key Lab Artificial Intelligence, Kunming, Yunnan, Peoples R China
基金
中国国家自然科学基金;
关键词
Aspect-level; position information; hierarchy attention mechanism; sentiment analysis; sentiment polarity;
D O I
10.3233/JIFS-211515
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The purpose of aspect-level sentiment analysis is to identify the contextual sentence expressions given by sentiment for some aspects. For previous works, many scholars have proved the importance of the interaction between aspects and contexts. However, most existing methods ignore or do not specifically capture the position information of the aspect targets in the sentence. Thus, we propose an aspect-level sentiment analysis based on joint aspect and position hierarchy attention mechanism network. At the same time, the model adopts a joint approach to make the model of the aspect features and the position features. On the one hand, this method clearly captures the interaction between aspect words and context when inputting word vector information. On the other hand, this method can enhance the importance of position information in the sentence and boost the information retrieval ability of the model. Additionally, the model utilizes a hierarchical attention mechanism to extract feature information and to differentiate sentiment towards, which is similar to filtering useless information again. Experiment on the SemEval 2014 dataset represent that our model achieves better performance on aspect-level sentiment classification.
引用
收藏
页码:2207 / 2218
页数:12
相关论文
共 50 条
  • [1] Joint Attention LSTM Network for Aspect-Level Sentiment Analysis
    Cai, Guoyong
    Li, Hongyu
    [J]. INFORMATION RETRIEVAL, CCIR 2018, 2018, 11168 : 147 - 157
  • [2] Revising Attention with Position for Aspect-Level Sentiment Classification
    Wang, Dong
    Liu, Tingwen
    Wang, Bin
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: TEXT AND TIME SERIES, PT IV, 2019, 11730 : 130 - 142
  • [3] A Multi-Attention Network for Aspect-Level Sentiment Analysis
    Zhang, Qiuyue
    Lu, Ran
    [J]. FUTURE INTERNET, 2019, 11 (07):
  • [4] Interactive Rule Attention Network for Aspect-Level Sentiment Analysis
    Lu, Qiang
    Zhu, Zhenfang
    Zhang, Dianyuan
    Wu, Wenqing
    Guo, Qiangqiang
    [J]. IEEE ACCESS, 2020, 8 : 52505 - 52516
  • [5] Bidirectional-GRU Based on Attention Mechanism for Aspect-level Sentiment Analysis
    Zhai Penghua
    Zhang Dingyi
    [J]. ICMLC 2019: 2019 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING, 2019, : 86 - 90
  • [6] Attention Capsule Network for Aspect-Level Sentiment Classification
    Deng, Yu
    Lei, Hang
    Li, Xiaoyu
    Lin, Yiou
    Cheng, Wangchi
    Yang, Shan
    [J]. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2021, 15 (04): : 1275 - 1292
  • [7] R-Transformer Network Based on Position and Self-Attention Mechanism for Aspect-Level Sentiment Classification
    Zhou, Ziyu
    Liu, Fang'ai
    Wang, Qianqian
    [J]. IEEE ACCESS, 2019, 7 : 127754 - 127764
  • [8] Co-attention networks based on aspect and context for aspect-level sentiment analysis
    Liu, MeiZhen
    Zhou, FengYu
    Chen, Ke
    Zhao, Yang
    [J]. KNOWLEDGE-BASED SYSTEMS, 2021, 217
  • [9] A novel network with multiple attention mechanisms for aspect-level sentiment analysis
    Wang, Xiaodi
    Tang, Mingwei
    Yang, Tian
    Wang, Zhen
    [J]. KNOWLEDGE-BASED SYSTEMS, 2021, 227
  • [10] Attention-Based Linguistically Constraints Network for Aspect-Level Sentiment
    Lu, Jinyu
    Hou, Yuexian
    [J]. PRICAI 2018: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II, 2018, 11013 : 282 - 289