LLM-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network for Sentiment Analysis
International Journal of Information Systems in the Service Sector · 04.09.2025 · 16 (1) · 1-15
DOI: 10.4018/ijisss.388002 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Information Systems in the Service Sector, erschienen am 04.09.2025. Verfasst von Yujie Jin und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Multimodal sentiment analysis aims to attain a precise comprehension of emotions by integrating complementary textual, visual, and audio information. However, issues such as sentiment discrepancies between modalities, ineffective integration of multi-modal information, and the intricacy of order dependency significantly constrain the models' efficacy. The authors propose an LLM-guided Hierarchical Spatio-Temporal Graph Network (L-HSTGN). By multimodal large model feature enhancement, bidirectional spatio-temporal joint modeling, and dynamic gate fusion mechanism, they effectively address the aforementioned problems. Firstly, they produce cross-modal emotion pseudo-labels based on the multimodal large model, and the single-modal representation was optimized by combining adversarial regularization. Secondly, they develop a bidirectional spatio-temporal convolution module to concurrently extract local-global temporal characteristics and dynamic spatial correlations.
Zitieren
APA
Jin, Y., Wang, Y., Wang, Y., Chen, Q., Hu, B., Han, Y., Ma, C., & Pedrycz, W. (2025). LLM-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network for Sentiment Analysis. International Journal of Information Systems in the Service Sector, 16(1), 1-15. https://doi.org/10.4018/ijisss.388002
Vancouver
Jin Y, Wang Y, Wang Y, Chen Q, Hu B, Han Y, et al. LLM-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network for Sentiment Analysis. International Journal of Information Systems in the Service Sector. 2025;16(1):1-15. doi:10.4018/ijisss.388002
BibTeX
@article{Jin2025,
author = {Jin, Yujie and Wang, Yong and Wang, Yuzhe and Chen, Qiyang and Hu, Bin and Han, Yanling and Ma, Chaoyin and Pedrycz, Witold},
title = {LLM-Guided Multimodal Information Fusion With Hierarchical Spatio-Temporal Graph Network for Sentiment Analysis},
journal = {International Journal of Information Systems in the Service Sector},
year = {2025},
volume = {16},
number = {1},
pages = {1--15},
doi = {10.4018/ijisss.388002}
}
EUVIMED