Modeling Trust for Recommender Systems using Similarity Metrics

摘要: In this paper we present novel techniques for modeling trust relationships that can be used in recommender systems. Such environments exist with the voluntary collaboration of community members who have as a common purpose provision accurate recommendations to each other. The performance such systems enhanced if potential between is properly exploited. This requires are appropriately established them. Our model provides link existing knowledge, expressed similarity metrics, and beliefs which required establishing community. Although explore challenge using an empirical approach, attempt comparison alternative candidate formulas aim finding optimal one. A statistical analysis evaluation results shows one best. We also compare our new same purpose.