Towards Improving (Meta)cognition by Adapting to Student Uncertainty in Tutorial Dialogue

Litman, Diane; Forbes-Riley, Kate

doi:10.1007/978-1-4419-5546-3_25

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have conducted a series of studies examining the benefits and challenges of building a spoken dialogue system that can detect and adapt to student uncertainty [19,20,21] and disengagement [22,23] during conceptual physics tutoring. Our adaptive dialogue system first detects uncertainty and/or disengagement in each student turn via learned models that use acousticprosodic features extracted from the speech signal, lexical features extracted from a noisy speech recognition transcript, as well as contextual features extracted from dialogue system logs to predict student states.…”

Section: Adapting To Student States In a Spokenmentioning

confidence: 99%

Enhancing the effectiveness of spoken dialogue for STEM education

Litman

2013

Speech and Language Technology in Education (SLaTE 2013)

View full text Add to dashboard Cite

This talk will discuss the application of speech and language processing to two types of STEM (Science, Technology, Engineering, and Mathematics) dialogue applications: 1) one-on-one physics tutoring, where students engage in dialogues with either a computer or human tutor, and 2) engineering design, where students engage in multi-party dialogue to complete a group project. I will first present results illustrating that relationships exist between student learning and both student affect, as well as lexical/prosodic entrainment between conversational partners. I will then illustrate our use of such findings to build better educational dialogue systems.

show abstract