The inherent weakness of the data on user ratings collected from the web, such as sparsity and cold-start, has limited the data analysis capability and prediction accuracy. To alleviate this problem, trust is incorporated in the CF approaches with encouraging experimental results. In this paper, we propose a computational model for trust-based CF with a method to generate and propagate trust in a social network. We apply this method to measure trusts on users’ ratings of hotels and show its feasibility by comparing the testing results with the traditional CF methods, e.g. Mean Absolute Error.