Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (6): 1786-1795.DOI: 10.11772/j.issn.1001-9081.2023050638

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Aspect-level sentiment analysis model combining strong association dependency and concise syntax

Tianci KE1,2, Jianhua LIU1,2(), Shuihua SUN1,2, Zhixiong ZHENG1,2, Zijie CAI1,2   

  1. 1.School of Computer Science and Mathematics,Fujian University of Technology,Fuzhou Fujian 350118,China
    2.Fujian Provincial Key Laboratory of Big Data Mining and Applications (Fujian University of Technology),Fuzhou Fujian 350118,China
  • Received:2023-05-24 Revised:2023-08-14 Accepted:2023-08-21 Online:2023-08-25 Published:2024-06-10
  • Contact: Jianhua LIU
  • About author:KE Tianci, born in 1999, M. S. candidate. His research interests include aspect-level sentiment analysis.
    SUN Shuihua, born in 1962, Ph. D., professor. Her research interests include natural language processing, machine translation.
    ZHENG Zhixiong, born in 1996, M. S. candidate. His research interests include natural language processing.
    CAI Zijie, born in 2000, M. S. candidate. His research interests include natural language processing.
  • Supported by:
    National Natural Science Foundation of China(62172095);Fujian Provincial Natural Science Foundation(2023J01349)

融合强关联依赖和简洁语法的方面级情感分析模型

柯添赐1,2, 刘建华1,2(), 孙水华1,2, 郑智雄1,2, 蔡子杰1,2   

  1. 1.福建理工大学 计算机科学与数学学院, 福州 350118
    2.福建省大数据挖掘与应用技术重点实验室(福建理工大学), 福州 350118
  • 通讯作者: 刘建华
  • 作者简介:柯添赐(1999—),男,福建莆田人,硕士研究生,CCF会员,主要研究方向:方面级情感分析
    孙水华(1962—),女,福建宁德人,教授,博士,主要研究方向:自然语言处理、机器翻译
    郑智雄(1996—),男,福建莆田人,硕士研究生,CCF会员,主要研究方向:自然语言处理
    蔡子杰(2000—),男,福建漳州人,硕士研究生,主要研究方向:自然语言处理。
  • 基金资助:
    国家自然科学基金资助项目(62172095);福建省自然科学基金资助项目(2023J01349)

Abstract:

In response to several issues related to the interference of multiple aspect words in the syntactic dependency tree, redundant information caused by invalid words and punctuation marks, as well as weak correlations between aspect words and corresponding sentiment words, an aspect-level sentiment analysis model combining Strong Association Dependencies and Concise Syntax (SADCS) was proposed. Firstly, a sentiment Part-Of-Speech (POS) list was constructed to enhance the association between aspect words and corresponding sentiments. Then, a joint list incorporating POS list and dependency relationships was constructed to eliminate redundant information of invalid words and punctuation marks in the optimized dependency tree. Next, optimized dependency tree was combined with a Graph ATtention network (GAT) to model and extract contextual features. Finally, contextual feature information and the feature information of dependency relationship types were learned and fused to enhance the feature representation, enabling the classifier to efficiently predict the sentiment polarity of each aspect word. The proposed model was experimentally analyzed on four public datasets. Compared with the DMF-GAT-BERT (Dynamic Multichannel Fusion mechanism based on the GAT and BERT (Bidirectional Encoder Representations from Transformers)) model, the accuracy of the proposed model increased by 1.48, 1.81, 0.09 and 0.44 percentage points, respectively. Experimental results demonstrate that the proposed model effectively enhances the association between aspect words and sentiment words, resulting in more accurate prediction of aspect word sentiment polarity.

Key words: aspect-level sentiment analysis, dependency relationship, Part-Of-Speech (POS), syntactic dependency tree, Graph ATtention network (GAT)

摘要:

针对语法依赖树存在多个方面词相互干扰的依赖信息、无效单词,以及标点符号带来的冗余信息和方面词与对应情感词之间的关联性较弱等问题,提出一种融合强关联依赖和简洁语法的方面级情感分析模型(SADCS)。首先,构建情感词性(POS)列表,通过该列表加强方面词与对应情感的相关性;其次,构建融合POS和依赖关系的联合列表,通过该联合列表去除已优化的依赖树无效单词与标点符号的冗余信息;再次,将优化后的依赖树与图注意力网络(GAT)结合建模提取上下文特征;最后,与依赖关系类型的特征信息进行交互学习并融合特征,增强特征表示,最终使分类器能高效预测每个方面词的情感极性。将所提模型在4个公开数据集上进行实验分析,与DMF-GAT-BERT(Dynamic Multichannel Fusion mechanism based on the GAT and BERT (Bidirectional Encoder Representations from Transformers))模型相比,所提模型的准确率分别提高了1.48、1.81、0.09和0.44个百分点。实验结果表明,所提模型能够有效增强方面词与情感词的联系,使方面词情感极性的预测更准确。

关键词: 方面级情感分析, 依赖关系, 词性, 语法依赖树, 图注意力网络

CLC Number: