CST-Net: community-guided structural-temporal convolutional networks for popularity prediction

doi:10.7717/peerj-cs.2931

	CST-Net: community-guided structural-temporal convolutional networks for popularity prediction
	Zheng, Xuxu 1,2; Bao, Peng 3; Qi, Lin 3; Tian, Chen 3; Shen, Huawei 1,2
	2025-06-26
发表期刊	PEERJ COMPUTER SCIENCE
卷号	11 页码:21
摘要	The ability to predict the popularity of online contents has important implications in a wide range of areas. The challenge of this problem comes from the inequality of the popularity of content and the numerous complex factors. Existing works fall into three main paradigms: feature-driven approaches, generative models, and methods based on deep learning, each with known strengths and limitations. In this article, we propose an end-to-end deep learning framework, called CST-Net, to combat the defects of existing methods. We first learn a low-dimensional embedding for each user based on historic interactions. Then, users are clustered into communities based on the learned user embeddings, and information cascades are represented as a series of episodes in the form of community interaction matrix. Afterwards, a convolutional architecture is applied to learn the representation of the entire information cascade. Finally, the extracted structural and temporal features are further combined to predict the incremental popularity. We validate the effectiveness of the proposed CST-Net by applying it on two different types of population-scale datasets, i.e., a microblogging dataset and an academic citation dataset. Experimental results demonstrate that the proposed CST-Net model consistently outperforms the existing competitive popularity prediction methods.
关键词	Information diffusion Popularity prediction Social network Neural networks
DOI	10.7717/peerj-cs.2931
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61263033] ; National Natural Science Foundation of China[U21B2046]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS记录号	WOS:001531886500001
出版者	PEERJ INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42085
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Bao, Peng
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Beijing Jiaotong Univ, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zheng, Xuxu,Bao, Peng,Qi, Lin,et al. CST-Net: community-guided structural-temporal convolutional networks for popularity prediction[J]. PEERJ COMPUTER SCIENCE,2025,11:21.
APA	Zheng, Xuxu,Bao, Peng,Qi, Lin,Tian, Chen,&Shen, Huawei.(2025).CST-Net: community-guided structural-temporal convolutional networks for popularity prediction.PEERJ COMPUTER SCIENCE,11,21.
MLA	Zheng, Xuxu,et al."CST-Net: community-guided structural-temporal convolutional networks for popularity prediction".PEERJ COMPUTER SCIENCE 11(2025):21.