Meta-evaluation of human-agent interactions using lens model analysis

In this paper, instead of taking conventional artificial intelligence approaches for an interface agent we propose a new designing method using the ecological approach since we would like to stress the importance or the agent´s ability to create reciprocal relationships with the human user (i.e., a social ability rather than its knowledgeable ability enclosed within the agent itself. We propose to use Brunswik´s lens model analysis to model. The agent´s meta-recognition mechanism. This is for measuring and quantifying sociality between the two decision-making agents (i.e., a human user and an interface agent). Based on this analysis. then, we designed an Agent that can infer the coordination level with a particular human. identify his/her skill levels. and adjust the level of shared situation awareness with its human partner.