A number of matchmaking methods have been proposed and used for various applications. However, the issues associated with matchmaking for web services that involve data repository are not well addressed by the existing methods which focus on service capabilities, interface signatures, and so on. This results from that the information and data in repository are not considered for matchmaking. In our previous work, we proposed a fuzzy matchmaking framework which exploits fuzzy logic to abstract and classify the underlying data of web services as fuzzy terms and rules. As a result, it increases the efficiency of the discovery of web services and allows imprecise or vague terms incorporated in the search. However, the assumption of unified (consensus) value between service providers and consumers for the service is made. In this paper, a fuzzy moderator is introduced in order to provide a tracking mechanism for feedbacks and moderate their values.