Application of Graph Neural Networks in Predicting Social Media Propagation Pathways

Qun Wang

doi:10.47297/taposatWSP2633-456903.20260705

PDF
Export
Share
Collection
Album

Application of Graph Neural Networks in Predicting Social Media Propagation Pathways

Volume 7, Issue 5

Views: 0 Downloads: 0

Application of Graph Neural Networks in Predicting Social Media Propagation Pathways
Application of Graph Neural Networks in Predicting Social Media Propagation Pathways
Communication University of China, Nanjing, School of Media Technology, Nanjing, Jiangsu, 211172, China
Vol. 7, Issue 5, Pages: 14-16(2026)
Online First：15 July 2026，

Published：30 May 2026
DOI：10.47297/taposatWSP2633-456903.20260705
Accepted：

Scan QR Code

Wang Qun.Application of Graph Neural Networks in Predicting Social Media Propagation Pathways[J].Theory and Practice of Science and Technology,2026,07(05):14-16.
DOI：

Wang Qun.Application of Graph Neural Networks in Predicting Social Media Propagation Pathways[J].Theory and Practice of Science and Technology,2026,07(05):14-16. DOI： 10.47297/taposatWSP2633-456903.20260705.

摘要

Abstract

Predicting social media propagation paths is of significant importance for guiding and controlling online public opinion. To overcome the limitations of traditional statistical models in handling non-Euclidean structured data

this paper proposes an optimized propagation prediction strategy based on graph neural networks. By analyzing network topological features

a node representation model integrating temporal dynamics and multimodal semantics is derived. The paper addresses challenges such as data sparsity

temporal evolution

and semantic gaps

demonstrating the effectiveness of multi-order aggregation

spatio-temporal attention

and cross-modal embedding strategies. Analysis reveals that graph neural networks significantly enhance prediction accuracy for information diffusion chains in complex networks

providing algorithmic support for public opinion early warning mechanisms.

关键词

Keywords

references

D. R. Wijaya and F. Afianti, "Information-theoretic ensemble feature selection with multi-stage aggregation for sensor array optimization," IEEE Sensors Journal, vol. 21 , no. 1 , pp. 476 – 489 , 2020 .

L. Waikhom and R. Patgiri, "A survey of graph neural networks in various learning paradigms: methods, applications, and challenges," Artificial Intelligence Review, vol. 56 , no. 7 , pp. 6295 – 6364 , 2023 .

M. Zhang, P. Li, Y. Xia, K. Wang, and L. Jin, "Labeling trick: A theory of using graph neural networks for multi-node representation learning," in Advances in Neural Information Processing Systems (NeurIPS), vol. 34 , pp. 9061 – 9073 , 2021 .

M. Rahevar, A. Ganatra, T. Saba, A. Rehman, and S. A. Bahaj, "Spatial–temporal dynamic graph attention network for skeleton-based action recognition," Applied Sciences, vol. 15 , no. 9 , p. 4929 , 2023 .

Z. Jin, J. Qian, Z. Kong, and C. Pan, "A mobility aware network traffic prediction model based on dynamic graph attention spatio-temporal network," Computer Networks, vol. 235 , p. 109981 , 2023 .

Alert me when the article has been cited

Submit

Emotion Recognition in Conversations: A Survey

A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks

Agenda Setting of Information Dissemination Regarding the Period of Nuclear Wastewater Discharge into the Sea on Social Media

Development Actuality and Trend Study of Social Media in China

A Review of Model Pruning Methods for Edge-Deployed MobileFaceNet

Related Author

Chanjuan Liu School of Information Technology and Engineering, Guangzhou College of Commerce

Guofu Liu School of Information Technology and Engineering, Guangzhou College of Commerce

Renhua Peng School of Information Technology and Engineering, Guangzhou College of Commerce

Lingyu Wang School of Arts and Sciences, China University of Petroleum-Beijing at Karamay

Nan Chen Jinan University

Mengyu Xiao

Yi Zhong

Related Institution

School of Information Technology and Engineering, Guangzhou College of Commerce

School of Arts and Sciences, China University of Petroleum-Beijing at Karamay

Jinan University

Department of Media & Communication, College of information engineering, Fuyang Normal University

⁰