Personalized recommendation based on time perception and users' feedback
Zhaonan Chen, Na Wang, Li Xia, Piao Chen · 2017
As the basis of human interactions, trust has been playing an influential role in addressing information sharing, experience communication, and public opinions. Trust-aware recommender systems are an effective solution to the information overload problem, especially in the online world where we are constantly faced with inordinately many choices. Based traditional rating prediction approach, this study focuses on constructing personalized recommendation by considering time perception and users' feedback. We present technical details about modeling trust evolution and perform experiments to show how the exploitation of trust evolution can help improve the performance of rating prediction and bring more robust solutions to the cold-start problem.