Trust Evaluation through Human-Machine Dialogue Modelling

摘要

Trust in automation, and particularly maintaining an adequate level of trust in automation is now recognized as a major performance factor in supervisory control. Leveraging mem-machine interaction is seen as a promising approach to influence the level of trust of an operator. Two problems need to be addressed in order to reach this goal: first measuring the level of trust; second acting on the level of trust to reach a more appropriate level. In this paper, we tackle the first problem, and propose to use a computational dialogue modelling approach to evaluate trust dynamically. We describe our model on two examples and give some perspectives.