Proceedings of the Annual Meeting of the Cognitive Science Society

Conversations with computer agents can be used to measure skills that may be difficult to accomplish using tra-ditional multiple-choice assessments. In order to achieve natural conversations in this form of assessment, we are exploringissues related to how test-takers interact with computer agents, such as what dialogue moves lead to interpretable responses,the influence of “cognitive characteristics” of computer agents, how should the system adapt to test-taker responses, and howthese interactions impact test-taker emotions and affect. In this presentation we will discuss our current research addressingthese questions, illustrating important dimensions that are involved with designing a conversation space and how each designdecision can impact multiple factors within assessment contexts.