Social trust is considered to be a promising mechanism to assist decision with uncertainty appearing in open society-based applications.User-specified social trust relations are often very sparse;therefore,inferring unknown social trust relations attracts increasing attention in recent years.Most existing work assumes that social trust relations are static.However,social trust,as a social concept,is intrinsically dynamic,and exploiting temporal dynamics provides challenges and opportunities for social trust prediction.In this paper,we investigate social trust prediction by exploiting temporal dynamics.In particular,we incorporate temporal dynamics in social trust prediction by modeling the dynamics of user preferences in two principled ways.We conduct experiments on a real-world dataset and the results demonstrate the effectiveness of our proposed models.Further experiments are conducted to understand the importance of temporal dynamics in social trust prediction.