An Adaptive Agent Model Estimating Human Trust in Information Sources

For an information agent to support a human in a personalized way, having a model of the trust the human has in information sources may be essential. As humans differ a lot in their characteristics with respect to trust, a trust model crucially depends on specific personalized values for a number of parameters. This paper contributes an adaptive agent model for trust with parameters that are automatically tuned over time to a specific individual. To obtain the adaptation, four different techniques have been developed. In order to evaluate these techniques, simulations have been performed. The results of these were formally verified.