Bootstrapping trust of Web services based on trust patterns and Hidden Markov Models

We propose in this paper a new approach for bootstrapping trust of Web services in which the interactions of a Web service with a user are observed during a certain time frame. The observations sequence is modeled as a Hidden Markov Model and matched against pre-defined trust patterns in order to assess the behavior of such Web service. The pre-defined trust patterns are specifications of possible behaviors of Web services such as trusted, malicious, betraying, oscillating, and redemptive. Based on the matching result, an initial trust value is assigned to the Web service. Our experimental results show that our approach enjoys good precision and recall values and provides a fair distribution of trust values. Besides, the proposed approach is applied on a dataset of real-world Web services. A comparative study with published bootstrapping approaches shows a better bootstrapping success rate for our new approach.