Context-Aware Ubiquitous Web Services Recommendation Based on User Location Update

In this paper, we propose a novel ubiquitous Web service recommendation approach to context-aware recommendation based on user location update (CASR-ULU). First, we model the influence of user location update based on user preference expansion. Second, we perform the context-aware similarity mining for updated location. Third, we predict the Quality of Service by Bayesian inference, and thus recommend the ideal Web service for the specific user subsequently. Furthermore, a calendar Android mobile application is implemented to testify the CASR-ULU algorithm in a ubiquitous environment. Finally, we evaluate the CASR-ULU method on WS-Dream dataset with evaluation matrices such as RMSE and MAE. Experimental results show that our method achieves competitive recommendation performance in a ubiquitous environment, compared to several state-of-the-art methods.