|Table of Contents|

Text Sentiment Analysis Based on Graph Neural Networks and Representation Learning(PDF)

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

Issue:
2024年03期
Page:
97-103
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Text Sentiment Analysis Based on Graph Neural Networks and Representation Learning
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)
Keywords:
text sentiment analysis; graph neural networks; representation learning; word embedding
PACS:
TP301
DOI:
10.3969/j.issn.1001-4616.2024.03.012
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.

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.

Memo

Memo:
-
Last Update: 2024-09-15