A cascade information diffusion prediction model integrating topic features and cross-attention

Abstract

Information cascade prediction is a crucial task in social network analysis. However, previous research has only focused on the impact of social relationships on cascade information diffusion, while ignoring the differences caused by the characteristics of cascade information itself, which limits the performance of prediction results. We propose a novel cascade information diffusion prediction model (Topic-HGAT). Firstly, we extract features from different topic features to enhance the learned cascade information representation. To better implement this method, we use hypergraphs to better characterize cascade information and dynamically learn multiple diffusion sub-hypergraphs according to the time process; secondly, we introduce cross-attention mechanisms to learn each other's feature representations from the perspectives of both user representation and cascade representation, thereby achieving deep fusion of the two features. This solves the problem of poor feature fusion effect caused by simply calculating self-attention on learned user representation and cascade representation in previous studies; finally, we conduct comparative experiments on four real datasets, including Twitter and Douban. Experimental results show that the proposed Topic-HGAT model achieves the highest improvements of 2.91% and 1.59% on Hits@100 and MAP@100 indicators, respectively, compared to other 8 baseline models, verifying the rationality and effectiveness of the proposed Topic-HGAT model.