文章详情

题名 · 作者 · 摘要 · 关键词 · DOI · 参考文献

基于门控注意力融合的图文多模态情感分析

宋玺文

(西安财经大学 信息学院,陕西 西安 710100)

栏目:人工智能 · 第 2026 年第 13 期 · 页码:54-59 · 2096-4706(2026)13-0054-06 · 中图分类号:TP391.1 · 文献标识码:A · DOI:10.19850/j.cnki.2096-4706.2026.13.011

摘要

针对图文多模态情感分析中文本与图像语义对齐不足、模态贡献难以动态平衡等问题,提出一种融合门控自注意力、双向模态间共注意力和自适应门控融合的情感分析模型(Multimodal Gated Attention for Cross-modal Learning Network, MGACL-Net)。分别利用RoBERTa和ResNet101提取文本与图像特征,通过模态内门控自注意力抑制噪声,再由双向共注意力建模图文交互,最后采用门控融合完成情感分类。在MVSA-Single和MVSA-Multiple数据集上进行对比实验与消融实验,结果表明模型在MVSA-Single上达到77.12%的准确率和76.92%的F1值。所提模型能够强化图文情感线索表达,提高跨模态融合的有效性与鲁棒性。

关键词

多模态情感分析;图文融合;跨模态注意力;自适应门控;情感分类

参考文献

  1. [1] Gandhi A,Adhvaryu K,Poria S,et al. MMultimodal Sentiment Analysis: A Systematic Review of History, Datasets, Multimodal Fusion Methods, Applications, Challenges and Future Directions [J].Information Fusion,2023,91:424-444.
  2. [2] 张亚洲,戎璐,宋大为,等.多模态情感分析研究综述 [J].模式识别与人工智能,2020,33(5):426-438.
  3. [3] Zhao K,Zheng M S,Li Q G,et al. Multimodal Sentiment Analysis—A Comprehensive Survey From a Fusion Methods Perspective [J].IEEE Access,2025:64556-64583.
  4. [4] 杨宇飞,钱育蓉,公维军,等.大模型优化的BERT图文多模态情感分析 [J].计算机系统应用,2025,34(8):62-69.
  5. [5] Hu H R. A Vision-Language Pre-training model based on Cross Attention for Multimodal Aspect-based Sentiment Analysis [C]//2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL),2024:370-375.
  6. [6] Li S T,Tang H. Multimodal Alignment and Fusion: A Survey [J/OL].arXiv:2411.17040 [cs.CV].https://doi.org/10.48550/arXiv.2411.17040.
  7. [7] Zhu Z Y,Jin Z B,Zhang J Y,et al. Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability [J/OL].arXiv:2502.14889 [cs.CV].https://doi.org/10.48550/arXiv.2502.14889.
  8. [8] Huang Z C,Zeng Z Y,Liu B,et al. Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers [J/OL].arXiv:2004.00849 [cs.CV].https://doi.org/10.48550/arXiv.2004.00849.
  9. [9] Radford A,Kim J W,Hallacy C,et al. Learning Transferable Visual Models From Natural Language Supervision [C]//Proceedings of the 38th International Conference on Machine Learning,2021:8748-8763.
  10. [10] Liang X,Yang E,Deng C,et al. CrossFormer: Cross-Modal Representation Learning via Heterogeneous Graph Transformer [J].ACM Transactions on Multimedia Computing, Communications and Applications,2024,20(12):1-21.
  11. [11] Feng X Y,Lin Y M,He L H,et al. Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis [J/OL].arXiv:2410.04491 [cs.CL].https://doi.org/10.48550/arXiv.2410.04491.
  12. [12] LI H C,LU Y T,ZHU H D. Multi-Modal Sentiment Analysis Based on Image and Text Fusion Based on Cross-Attention Mechanism [J/OL].Electronics,2024,13(11):2069.https://doi.org/10.3390/electronics13112069.
  13. [13] 张昱,张海军,刘雅情,等.基于双向掩码注意力机制的多模态情感分析 [J].数据分析与知识发现,2023,7(4):46-55.
  14. [14] 吕学强,田驰,张乐,等.融合多特征和注意力机制的多模态情感分析模型 [J].数据分析与知识发现,2024,8(5):91-101.

作者简介

宋玺文(2001—),女,汉族,陕西西安人,硕士研究生在读,研究方向:自然语言处理、情感分类。