EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SAGA-Net: A Similarity-Aware Aspect-Guided Relation Graph Network for Multimodal Aspect-Based Sentiment Analysis

Yanrong Zhang, Qingzhao Zhu, Binbin Zhao, Youbo Lyu, Wenrui Zhang

Applied Sciences · 20.11.2026 · 16 (22) · 11526

DOI: 10.3390/app162211526 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 20.11.2026. Verfasst von Yanrong Zhang und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Heilongjiang Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal aspect-based sentiment analysis (MABSA) is challenged by visual noise, as images in social media posts are often irrelevant to, weakly related to, or only partially informative for specific textual targets. Although existing methods attempt to fuse heterogeneous textual and visual information, their reliance on global visual representations or implicit feature fusion may be insufficient to filter weakly related visual cues, thereby limiting fine-grained aspect-level reasoning. To address these issues, this paper proposes SAGA-Net, a unified Similarity-Aware Aspect-Guided Relation Graph Network for MABSA. SAGA-Net first estimates aspect-specific visual reliability to dynamically suppress unreliable visual information before multimodal fusion. It then employs a cross-modal aspect-guided alignment module, where aspect representations serve as semantic queries to extract aspect-relevant visual evidence from region-level features. Furthermore, SAGA-Net constructs a heterogeneous aspect-text-visual graph and introduces a relation-aware graph attention network that incorporates edge weights into attention computation for explicit evidence propagation. Extensive experiments on Twitter-2015 and Twitter-2017 across three core tasks, including JMASA, MATE, and MASC, show that SAGA-Net achieves competitive performance against representative baselines. Additional ablation and diagnostic analyses further validate the effectiveness of visual reliability estimation, aspect-guided evidence selection, and structured cross-modal relation modeling.

Förderung

  • Heilongjiang Provincial Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Zhu, Q., Zhao, B., Lyu, Y., & Zhang, W. (2026). SAGA-Net: A Similarity-Aware Aspect-Guided Relation Graph Network for Multimodal Aspect-Based Sentiment Analysis. Applied Sciences, 16(22), 11526. https://doi.org/10.3390/app162211526

Vancouver

Zhang Y, Zhu Q, Zhao B, Lyu Y, Zhang W. SAGA-Net: A Similarity-Aware Aspect-Guided Relation Graph Network for Multimodal Aspect-Based Sentiment Analysis. Applied Sciences. 2026;16(22):11526. doi:10.3390/app162211526

BibTeX
@article{Zhang2026,
  author = {Zhang, Yanrong and Zhu, Qingzhao and Zhao, Binbin and Lyu, Youbo and Zhang, Wenrui},
  title = {SAGA-Net: A Similarity-Aware Aspect-Guided Relation Graph Network for Multimodal Aspect-Based Sentiment Analysis},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11526},
  doi = {10.3390/app162211526}
}
Kostenlos starten →