Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 42, 2025 No. 9
2707-2713

Multimodal aspect-level sentiment analysis based on cross-modal interaction Transformer

Gan Zhuohao1a
Miao Yuqing1a,1b,1c
Liu Tonglai2
Zhang Wanzhen2
Zhou Ming3
1. a. School of Computer Science & Information Security, b. Guangxi Key Laboratory of Image & Graphics Intelligent Processing, c. Guangxi Key Laboratory of Cryptography & Information Security, Guilin University of Electronic Technology, Guilin Guangxi 541004, China
2. College of Artificial Intelligence, Zhongkai University of Agriculture & Engineering, Guangzhou 510225, China
3. Guilin Hivision Technology Company, Guilin Guangxi 541004, China
DOI: 10.19734/j.issn.1001-3695.2024.11.0517

Abstract

To address the issues of insufficient visual information extraction and the lack of aspect sentiment semantics in existing multimodal aspect-level sentiment analysis models, this paper proposed a multimodal aspect-level sentiment analysis model based on cross-modal interaction Transformer(CMIT). The model used a text semantic enhancement module to integrate image captions with the original text, compensating for missing sentiment semantics. It constructed an aspect-aware feature extraction module using dependency syntax analysis and graph convolutional networks(GCN) to capture long-distance dependencies between aspect terms and opinion words. It designed a cross-modal feature interaction module, combining a top-n adjective-noun pair distribution constraint strategy and a multimodal fusion Transformer to achieve deep interaction between image and text features. Experimental results on the Twitter-2015, Twitter-2017 and ZOL datasets demonstrate that CMIT model outperforms several baseline models in both accuracy and macro-average F1-score, validating its effectiveness and gene-ralization ability.

Foundation Support

国家自然科学基金项目(62366010,62366011)
广东省研究生教育创新计划项目(2022JGXM115)
教育部产学合作协同育人项目(202102191071,202102211021)
桂林电子科技大学研究生教育创新计划项目(2024YCXS068)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.11.0517
Publish at: Application Research of Computers Printed Article, Vol. 42, 2025 No. 9
Section: Algorithm Research & Explore
Pages: 2707-2713
Serial Number: 1001-3695(2025)09-019-2707-07

Publish History

[2025-03-25] Accepted Paper
[2025-09-05] Printed Article

Cite This Article

甘卓浩, 缪裕青, 刘同来, 等. 基于跨模态交互Transformer的多模态方面级情感分析 [J]. 计算机应用研究, 2025, 42 (9): 2707-2713. (Gan Zhuohao, Miao Yuqing, Liu Tonglai, et al. Multimodal aspect-level sentiment analysis based on cross-modal interaction Transformer [J]. Application Research of Computers, 2025, 42 (9): 2707-2713. )

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)