In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 41, 2024 No. 11
3295-3302

Multi-feature multiple fusion sentiment classification model based on syntactic dependency and attention mechanism

Xia Jialia
Yu Zikaia
Deng Qingshana
Liu Dexib
Peng Wenzhongb
Luo Wenjuna
a. School of Software & Internet of Things Engineering, b. School of Information Management, Jiangxi University of Finance & Economics, Nanchang 330013, China
DOI: 10.19734/j.issn.1001-3695.2024.04.0104

Abstract

In response to the difficulty of existing deep learning models in extracting rich semantic information from online review, which hinders accurate sentiment extraction, this paper proposed a multi-feature multiple fusion sentiment classification model based on syntactic dependencies and attention mechanisms called MF-SDAM. Firstly, this model utilized syntactic dependency relationships to extract the aspect-opinion pairs of information from the text. Then, it employed the dynamic word embedding model BERT to obtain dynamic feature vector representations of online review. Next, based on a dual-channel feature extraction strategy, the model utilized a convolutional neural network(TextCNN) and a bidirectional long short-term memory network with attention mechanism(Att-BiLSTM) to extract local and global semantic features of the text. To further extract global semantic information, it concatenated the text features and the output features of Att-BiLSTM, and used the attention mechanism to weight the sentiment features. Finally, it employed a complementary feature fusion strategy with multiple fusion methods to fuse the local and global semantic features, reducing the problem of key information loss. It selected three real publicly available online review datasets from the food delivery and hotel domains for performance verification. Experimental results indicate that the performance of MF-SDAM in sentiment classification tasks for online review is outstanding, with its accuracy and F1-score are superior to the 10 baseline models in most cases. Moreover, it exhibits good robustness for imbalanced datasets.

Foundation Support

国家自然科学基金资助项目(62272206)
江西省教育厅科学技术研究项目(GJJ2200560)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.04.0104
Publish at: Application Research of Computers Printed Article, Vol. 41, 2024 No. 11
Section: Algorithm Research & Explore
Pages: 3295-3302
Serial Number: 1001-3695(2024)11-013-3295-08

Publish History

[2024-08-05] Accepted Paper
[2024-11-05] Printed Article

Cite This Article

夏家莉, 余子恺, 邓庆山, 等. 基于句法依存和注意力机制的多特征多重融合情感分类模型 [J]. 计算机应用研究, 2024, 41 (11): 3295-3302. (Xia Jiali, Yu Zikai, Deng Qingshan, et al. Multi-feature multiple fusion sentiment classification model based on syntactic dependency and attention mechanism [J]. Application Research of Computers, 2024, 41 (11): 3295-3302. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)