Spoken Tutorial Dialogue and the Feeling of Another's Knowing

We hypothesize that monitoring the accuracy of the "feeling of another's knowing" (FOAK) is a useful predictor of tutorial dialogue system performance. We test this hypothesis in the context of a wizarded spoken dialogue tutoring system, where student learning is the primary performance metric. We first present our corpus, which has been annotated with respect to student correctness and uncertainty. We then discuss the derivation of FOAK measures from these annotations, for use in building predictive performance models. Our results show that monitoring the accuracy of FOAK is indeed predictive of student learning, both in isolation and in conjunction with other predictors