Aggregating Ordinal User Preferences for Effective Reputation Computation of Online Services

Reputation systems have become an important means to help users build trust, reduce information asymmetry and filter information in the context of online services provision. Different users cannot rate services under the same criteria due to the scale and dynamism of these systems. Thus, aggregating cardinal ratings into reputation will potentially lead to unreliable and misleading result, which makes reputation systems necessarily consider the impossibility of interpersonal utility comparisons. In this paper, we exploit the ordinal user preferences between services to compute reputation of services. A distance metric is defined to measure the discrepancy between two rating vectors and the reputation computation problem was formalized as an optimization problem. Then, genetic algorithm is used to solve the optimization problem to find a reputation vector that minimizes the total number of disagreements with the rating matrix. We conduct a comprehensive experimental study and performance analysis to evaluate the effectiveness and efficiency of the proposed method.