User Features-aware Trust Measurement of Cloud Services via Evidence Synthesis for Potential Users

The cloud computing paradigm can provide elastic and dynamic resources on demand, which facilitates service providers to make profits resulting from the long tail effect. So it is vitally important to ensure that cloud services can be acceptable to more and more potential users. However, it is challenging for potential users to discover the trustworthy cloud services due to the deficiency of usage experiences and the information overload of QoE evaluations from consumers. This paper proposed a user features-aware trust measurement approach for potential users. In this approach, the influence factors of QoE are systematically analyzed based on user feature model and the quantitative computation methods are designed to measure the user feature similarity. In addition, employing FAHP method identifies the user feature community. To enhance the accuracy of trust measurement, the false evidences in the QoE evaluations are iteratively filtered with dynamic mean distance threshold. Finally, the service trust is measured via evidence synthesis combining user feature similarity. The experiments show that this approach is effective to improve the quality of trust measurement, which is helpful to solve the cold start problem and data fusion problem with false evidences in cloud computing paradigm. Keywords-cloud services, trust measurement, user features, potential users, evidence synthesis