Understanding information diffusion with psychological field dynamic
作者：
Highlights：
• An effective convolution method is proposed to extract the semantic relationship.
• We design a cross infusion mechanism to fuse the individual dynamic embeddings.
• A sophisticated aggregation strategy is introduced to generate cascade embedding.
• The dynamic variation and cross dependencies are observed by model analysis.
摘要
•An effective convolution method is proposed to extract the semantic relationship.•We design a cross infusion mechanism to fuse the individual dynamic embeddings.•A sophisticated aggregation strategy is introduced to generate cascade embedding.•The dynamic variation and cross dependencies are observed by model analysis.
论文关键词：Information diffusion,Psychological field dynamics,Cross infusion,Deep learning
论文评审过程：Received 4 November 2021, Revised 9 April 2022, Accepted 23 April 2022, Available online 11 May 2022, Version of Record 11 May 2022.
论文官网地址：https://doi.org/10.1016/j.ipm.2022.102956
