Virtual agents have been shown to be more effective when incorporating social factors such as trust into task action selection. However, there has been less work on how virtual tutoring agents can incorporate social factors into pedagogical action selection. We propose and evaluate how a socially-conditioned task reasoner for a virtual pedagogical…

In this study, the Bystander Turing Test (BTT) paradigm is used to determine whether participants rate particular dialog moves in tutoring transcripts to be generated by a computer tutor, AutoTutor, or by a skilled human tutor. Currently, AutoTutor initiates a conversation with the learner by posing a question or presenting a problem for the…