EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Public Opinion Propagation Prediction Model Based on Dynamic Time-Weighted Rényi Entropy and Graph Neural Network

Qiujuan Tong, Xiaolong Xu iD, Jianke Zhang iD, Huawei Xu

Entropy · 12.05.2025 · 27 (5) · 516

DOI: 10.3390/e27050516 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 12.05.2025. Verfasst von Qiujuan Tong und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Science, Xi'an University of Posts and Telecommunications, Xi'an 710121, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key R&D Program Project of Shaanxi Province, China, Science and technology plan project of Xi'an, China, Xi 'an University of Posts and Telecommunications Graduate Innovation Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current methods for public opinion propagation prediction struggle to jointly model temporal dynamics, structural complexity, and dynamic node influence in evolving social networks. To overcome these limitations, this paper proposes a public opinion dissemination prediction model based on the integration of dynamic time-weighted Rényi entropy (DTWRE) and graph neural networks. By incorporating a time-weighted mechanism, the model devises two tiers of Rényi entropy metrics—local node entropy and global time-step entropy—to effectively quantify the uncertainty and complexity of network topology at different time points. Simultaneously, by integrating DTWRE features with high-dimensional node embeddings generated by Node2Vec and utilizing GraphSAGE to construct a spatiotemporal fusion modeling framework, the model achieves precise prediction of link formation and key node identification in public opinion dissemination. The model was validated on multiple public opinion datasets, and the results indicate that, compared to baseline methods, it exhibits significant advantages in several evaluation metrics such as AUC, thereby fully demonstrating the effectiveness of the dynamic time-weighted mechanism in capturing the temporal evolution of public opinion dissemination and the dynamic changes in network structure.

Schlagwörter

Stichwörter der Autor:innen

dynamic time-weighted Rényi entropygraph neural networksnode embeddingspublic opinion predictionspatiotemporal fusion modeling

Autor:innen und Institutionen

  • School of Science, Xi'an University of Posts and Telecommunications, Xi'an 710121, China.
  • School of Communication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an 710121, China.

ORCID-Profile: Xiaolong Xu, Jianke Zhang

Förderung

  • Key R&D Program Project of Shaanxi Province, China
  • Science and technology plan project of Xi'an, China
  • Xi 'an University of Posts and Telecommunications Graduate Innovation Fund
  • Key R&D Program Project of Shaanxi Province, China
  • Science and technology plan project of Xi’an, China
  • Xi’an University of Posts and Telecommunications Graduate Innovation Fund
  • Basic Natural Science Research Program of Shaanxi Province, China

Zitieren

APA

Tong, Q., Xu, X., Zhang, J., & Xu, H. (2025). Public Opinion Propagation Prediction Model Based on Dynamic Time-Weighted Rényi Entropy and Graph Neural Network. Entropy, 27(5), 516. https://doi.org/10.3390/e27050516

Vancouver

Tong Q, Xu X, Zhang J, Xu H. Public Opinion Propagation Prediction Model Based on Dynamic Time-Weighted Rényi Entropy and Graph Neural Network. Entropy. 2025;27(5):516. doi:10.3390/e27050516

BibTeX
@article{Tong2025,
  author = {Tong, Qiujuan and Xu, Xiaolong and Zhang, Jianke and Xu, Huawei},
  title = {Public Opinion Propagation Prediction Model Based on Dynamic Time-Weighted Rényi Entropy and Graph Neural Network},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {5},
  pages = {516},
  doi = {10.3390/e27050516}
}
Kostenlos starten →