EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SGMLN: Sentiment-Guided Mutual Learning Network for Multimodal Sarcasm Detection

Yiran Wang iD, Xin Zhao iD, Yongtang Bao iD

Sensors · 08.04.2026 · 26 (8) · 2304

DOI: 10.3390/s26082304 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 08.04.2026. Verfasst von Yiran Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qingdao Science and Technology for the People Demonstration Project, Natural Science Foundation of Shandong Province, Taishan Scholar Program of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Social networks such as Twitter have grown rapidly and are now flooded with sarcastic comments, both in text and in images. Detecting sarcasm in multimodal data has significant social value and is attracting increasing research attention. However, most studies overlook the role of sentiment, even though sentiment information in text is closely linked to clues of sarcasm. Additionally, few consider how text and images align semantically. To address these issues, we propose a sentiment-guided mutual learning network (SGMLN) for multimodal sarcasm detection. SGMLN utilizes sentiment information to inform the combination of text and image features, and employs mutual learning to facilitate knowledge sharing among classifiers. We design a sentiment-guided attention layer that injects sentiment into both modalities, producing features that capture sarcasm more effectively. Sentic-BERT extracts sentiment-aware vectors from text, using word-level sentiment as a mask. In mutual learning, a logistic distribution function measures differences between classifiers, improving knowledge transfer between modalities. This step boosts multimodal understanding and model performance. By introducing sentiment-aware representations and semantic alignment, SGMLN bridges the gap between text and images, making them more consistent. Experiments on public datasets demonstrate that our model is effective and outperforms alternatives.

Schlagwörter

Stichwörter der Autor:innen

multimodal fusionmultimodal sarcasm detectionmutual learningsentiment-guided

Autor:innen und Institutionen

  • College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China.

ORCID-Profile: Yiran Wang, Xin Zhao, Yongtang Bao

Förderung

  • Qingdao Science and Technology for the People Demonstration Project
  • Natural Science Foundation of Shandong Province
  • Taishan Scholar Program of Shandong Province
  • Qingdao Natural Science Foundation
  • alented Young Teachers Training Program of Shandong University of Science and Technology

Zitieren

APA

Wang, Y., Zhao, X., & Bao, Y. (2026). SGMLN: Sentiment-Guided Mutual Learning Network for Multimodal Sarcasm Detection. Sensors, 26(8), 2304. https://doi.org/10.3390/s26082304

Vancouver

Wang Y, Zhao X, Bao Y. SGMLN: Sentiment-Guided Mutual Learning Network for Multimodal Sarcasm Detection. Sensors. 2026;26(8):2304. doi:10.3390/s26082304

BibTeX
@article{Wang2026,
  author = {Wang, Yiran and Zhao, Xin and Bao, Yongtang},
  title = {SGMLN: Sentiment-Guided Mutual Learning Network for Multimodal Sarcasm Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2304},
  doi = {10.3390/s26082304}
}
Kostenlos starten →