EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TDGN: A text-guided dual-gated network for multimodal sentiment analysis

Wenyan Xiao, Lin Zhang iD, Yangshuyi Xu iD

PLOS One · 12.05.2026 · 21 (5) · e0349024

DOI: 10.1371/journal.pone.0349024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.05.2026. Verfasst von Wenyan Xiao und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Shanghai Maritime University, Shanghai, China. Hauptthemen laut MEDLINE: Emotions, Neural Networks, Computer. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal Sentiment Analysis (MSA) aims to interpret emotions by integrating textual, acoustic, and visual information. However, the heterogeneous quality and weak correlation among nonverbal modalities often lead to unstable alignment and ineffective fusion. To address these challenges, we propose a Text-Guided Dual-Gated Network (TDGN) that introduces a hierarchical gating and text-anchored contrastive learning framework. During the alignment phase, a Text-Anchored Gated Attention (TGA) module employs text as a semantic anchor to guide fine-grained alignment between audio and visual modalities while suppressing noise and emphasizing salient emotional cues. For the fusion stage, a Dual-layer Gated Fusion (DGF) module performs intra-modal gating to refine modality-specific features and inter-modal gating to dynamically balance cross-modal contributions. Furthermore, we introduce a Text-Anchored Contrastive Learning (TACL), which constructs contrastive targets based on textual similarity anchors, ensuring the fused features maintain both modal consistency and modal diversity. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that TDGN achieves state-of-the-art performance, achieving higher accuracy and robustness. Ablation studies and visualization further validate the effectiveness of each component.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsNeural Networks, ComputerHumansSemanticsAlgorithms

Autor:innen und Institutionen

  • College of Information Engineering, Shanghai Maritime University, Shanghai, China.

ORCID-Profile: Lin Zhang, Yangshuyi Xu

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xiao, W., Zhang, L., & Xu, Y. (2026). TDGN: A text-guided dual-gated network for multimodal sentiment analysis. PLOS One, 21(5), e0349024. https://doi.org/10.1371/journal.pone.0349024

Vancouver

Xiao W, Zhang L, Xu Y. TDGN: A text-guided dual-gated network for multimodal sentiment analysis. PLOS One. 2026;21(5):e0349024. doi:10.1371/journal.pone.0349024

BibTeX
@article{Xiao2026,
  author = {Xiao, Wenyan and Zhang, Lin and Xu, Yangshuyi},
  title = {TDGN: A text-guided dual-gated network for multimodal sentiment analysis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0349024},
  doi = {10.1371/journal.pone.0349024}
}
Kostenlos starten →