Heterogeneous information network embedding for user behavior analysis on social media

User behavior prediction with low-dimensional vectors generated by user network embedding models has been verified to be efficient and reliable in real applications. However, existing graph representation learning methods mainly focus on homogeneous and static graphs and cannot well represent the real-world social networks that are heterogeneous and keep evolving. To address this challenge, we propose a dynamic heterogeneous user behavior analysis network (DHBN) model, which applies graph network embedding to fuse multi-networks information by considering their heterogeneity and evolutionary patterns over dynamic networks. In particular, by separately performing user social relationship embedding, node attribute embedding and user behavior embedding, the proposed scheme learns the highly nonlinear representations of network nodes; and then we explore recurrent neural networks based on attention mechanism to capture the networks' dynamic evolution. Our proposed method has been examined on two real-world datasets, and five state-of-the-art schemes are compared to the proposed scheme for link prediction quality and node recommendation. Especially, for dynamic user behavior link prediction task on Weibo-UBA dataset, DHBN model achieves AUROC of 77.3% and AUPOC of 71.2%. In terms of AUROC, DHBN is at least 5% better than other models, the other experimental results also demonstrate that the DHBN model has significant advantages over other comparison models. This work can provide guidance on the future user behavior prediction studies.