[1]尹帮治,徐 健,唐超尘.基于图神经网络与表示学习的文本情感分析[J].南京师大学报(自然科学版),2024,(03):97-103.[doi:10.3969/j.issn.1001-4616.2024.03.012]
　Yin Bangzhi,Xu Jian,Tang Chaochen.Text Sentiment Analysis Based on Graph Neural Networks and Representation Learning[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(03):97-103.[doi:10.3969/j.issn.1001-4616.2024.03.012]
点击复制

基于图神经网络与表示学习的文本情感分析()
分享到：

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

卷:
期数:
2024年03期
页码:
97-103
栏目:
计算机科学与技术
出版日期:
2024-09-15

文章信息/Info

Title:
Text Sentiment Analysis Based on Graph Neural Networks and Representation Learning
文章编号:
1001-4616(2024)03-0097-07
作者:
尹帮治1; 徐 健2; 唐超尘3; 4
(1.邵阳职业技术学院,信息技术学院,湖南 邵阳 422000)
(2.桂林电子科技大学机电工程学院,广西 桂林 541001)
(3.桂林理工大学物理与电子信息工程学院,广西 桂林 541004)
(4.西安电子科技大学通信工程学院,陕西 西安 710071)
Author(s):
Yin Bangzhi1; Xu Jian2; Tang Chaochen3; 4
(1.School of Information Technology,Shaoyang Polytechnic,Shaoyang 422000,China)
(2.School of Mechanical and Electrical Engineering,Guilin University of Electronic Science and Technology,Guilin 541001,China)
(3.School of Physics and Electronic Information Engineering,Guilin University of Technology,Guilin 541004,China)
(4.School of Communication Engineering,Xidian University,Xi'an 710071,China)
关键词:
文本情感分析; 图神经网络; 表示学习; 词嵌入
Keywords:
text sentiment analysis; graph neural networks; representation learning; word embedding
分类号:
TP301
DOI:
10.3969/j.issn.1001-4616.2024.03.012
文献标志码:
A
摘要:
近年来,情感分析是近年来自然语言处理领域备受学者关注的核心研究方向,传统文本情感分析模型只能捕捉文本的表面特征,在不同领域或语境下缺乏泛化能力,难以处理长文本以及语义歧义等问题. 针对上述问题,本文设计了基于图神经网络与表示学习的文本情感分析模型(a text sentiment analysis model based on graph neural networks and representation learning,GNNRL). 利用Spacy生成句子的语法依赖树,利用图卷积神经网络进行编码,以捕捉句子中词语之间更复杂的关系; 采用动态k-max池化进一步筛选特征,保留文本相对位置的序列特征,避免部分特征损失的问题,从而提高模型的特征提取能力. 最后将情感特征向量输送到分类器SoftMax中,根据归一化后的值来判断情感分类. 为验证本文所提GNNRL模型的有效性,采用OS10和SMP2020两个文本情感分析数据集进行测试,与HyperGAT、IBHC、BERT_CNN、BERT_GCN、TextGCN模型比较,结果表明,综合accuracy、precision、recall、f1 4个指标,本文改进的AM_DNN模型均优于其他模型,在文本情感中具有较好的分类性能,并探究了不同优化器的选择对本模型的影响.
Abstract:
In recent years,sentiment analysis has become a core research direction in the field of natural language processing. Traditional text sentiment analysis models can only capture the surface features of text,and lack generalization ability in different fields or contexts,making it difficult to deal with long text and semantic ambiguity. In response to the above problems,A Text Sentiment Analysis Model Based on Graph Neural Networks and Representation Learning(GNNRL)is designed in this paper. Spacy is used to generate syntactic dependency tree of sentences,and graph convolutional neural network is used for coding to capture more complex relationships between words in sentences. Dynamic k-max pooling is used to further screen features,retain the sequence features of text relative position,and avoid the problem of partial feature loss,so as to improve the feature extraction ability of the model. Finally,the emotion feature vector is transferred to the classifier SoftMax,and the emotion classification is judged according to the normalized value. In order to verify the validity of the GNNRL model proposed in this paper,two text sentiment analysis datasets OS10 and SMP2020 are used for testing. Compared with HyperGAT,IBHC,BERT_CNN,BERT_GCN and TextGCN models,the results show that by synthesizing accuracy,precision,recall and f1,the improved AM_DNN model in this paper is superior to other models and has better classification performance in text emotion. Moreover,the influence of the selection of different optimizers on this model is explored.

参考文献/References:

[1]LI H,MA Y,MA Z,et al. Weibo text sentiment analysis based on bert and deep learning[J]. Applied sciences,2021,11(22):10774.
[2]LI Y,LI N. Sentiment analysis of Weibo comments based on graph neural network[J]. IEEE access,2022,10:23497-23510.
[3]YANG X,XU S,WU H,et al. Sentiment analysis of Weibo comment texts based on extended vocabulary and convolutional neural network[J]. Procedia computer science,2019,147:361-368.
[4]王珊,黄海燕,乔伟涛. 基于Reformer模型的文本情感分析[J]. 计算机工程与设计,2022,43(4):1089-1095.
[5]JIA W,PENG J. The public sentiment analysis of double reduction policy on weibo platform[J]. Computational intelligence and neuroscience,2022,2022(1):3212681.
[6]SADR H,PEDRAM M M,TESHNEHLAB M. Convolutional neural network equipped with attention mechanism and transfer learning for enhancing performance of sentiment analysis[J]. Journal of AI and data mining,2021,9(2):141-151.
[7]BASIRI M E,NEMATI S,ABDAR M,et al. A novel fusion-based deep learning model for sentiment analysis of COVID-19 tweets[J]. Knowledge-based systems,2021,228:107242.
[8]ANTONAKAKI D,FRAGOPOULOU P,IOANNIDIS S. A survey of Twitter research:Data model,graph structure,sentiment analysis and attacks[J]. Expert systems with applications,2021,164:114006.
[9]CHINY M,CHIHAB M,BENCHAREF O,et al. LSTM,VADER and TF-IDF based hybrid sentiment analysis model[J]. International journal of advanced computer science and applications,2021,12(7):11-22.
[10]李全鑫,庞俊,朱峰冉. 结合Bert与超图卷积网络的文本分类模型[J]. 计算机工程与应用,2023,59(17):107-115.
[11]DANG N C,MORENO-GARCÍA,MARÍA N,et al. Sentiment analysis based on deep learning:a comparative study[J]. Electronics,2020,9(3):483.
[12]李文彬,许雁玲,钟志楷,等. 基于稳定学习的图神经网络模型[J]. 湖南理工学院学报(自然科学版),2023,36(4):16-18.
[13]魏苏波,张顺香,朱广丽,等. 基于正交投影的BiLSTM-CNN情感特征抽取方法[J]. 南京师大学报(自然科学版),2023,46(1):139-148.
[14]李青,王一晨,杜承烈. 图表示学习方法研究综述[J]. 计算机应用研究,2023,40(6):1601-1613.
[15]邹然,柳杨,李聪,等. 图表示学习综述[J]. 北京师范大学学报(自然科学版),2023,59(5):716-724.
[16]陈豪伶,虞慧群,范贵生,等. 基于分层表示和上下文增强的类摘要生成技术[J]. 计算机研究与发展,2024,61(2):307-323.
[17]BASIRI M E,NEMATI S,ABDAR M,et al. ABCDM:An attention-based bidirectional CNN-RNN deep model for sentiment analysis[J]. Future generation computer systems,2021,115:279-294.
[18]JIAWA Z,WEI L,SILI W,et al. Review of methods and applications of text sentiment analysis[J]. Data analysis and knowledge discovery,2021,5(6):1-13.
[19]SINGLA C,AL-WESABI F N,PATHANIA Y S,et al. An optimized deep learning model for emotion classification in tweets[J]. Computers,materials & continua,2022,70(3):118-131.

相似文献/References:

[1]柴变芳,李 政,赵晓鹏,等.基于泛化图卷积神经网络的深度文档聚类模型[J].南京师大学报(自然科学版),2024,(01):82.[doi:10.3969/j.issn.1001-4616.2024.01.010]
　Chai Bianfang,Li Zheng,Zhao Xiaopeng,et al.Deep Document Clustering Model Based on Generalization Graph Convolutional Neural Network[J].Journal of Nanjing Normal University(Natural Science Edition),2024,(03):82.[doi:10.3969/j.issn.1001-4616.2024.01.010]

备注/Memo

备注/Memo:
收稿日期:2023-05-06.
基金项目:国家自然科学基金项目(61474032)、桂林医学院博士启动基金项目(31304019011).
通讯作者:尹帮治,博士,副教授,研究方向:深度学习,数据分析. E-mail:ybzdoc@163.com
更新日期/Last Update: 2024-09-15