LNCS 6094 - Characterizing the Effectiveness of Tutorial Dialogue with Hidden Markov Models

Characterizing the Effectiveness of Tutorial Dialogue with Hidden Markov Models 1,∗ 1,2 3 1Kristy Elizabeth Boyer , Robert Phillips , Amy Ingram , Eun Young Ha , 1,2 1 1Michael Wallis , Mladen Vouk , and James Lester 1 Department of Computer Science, North Carolina State University 2 Applied Research Associates, Inc. 3 Department of Mathematics and Computer Science, Meredith College Raleigh, North Carolina, USA keboyer@ncsu.edu Abstract. Identifying effective tutorial dialogue strategies is a key issue for in-telligent tutoring systems research. Human-human tutoring offers a valuable model for identifying effective tutorial strategies, but extracting them is a chal-lenge because of the richness of human dialogue. This paper addresses that challenge through a machine learning approach that 1) learns tutorial strategies from a corpus of human tutoring, and 2) identifies the statistical relationships between student outcomes and the learned strategies. We have applied hidden Markov modeling to a corpus of annotated task-oriented tutorial dialogue to learn one model for each of two effective human tutors. We have identified sig-nificant correlations between the automatically extracted tutoring modes and student learning outcomes. This work has direct applications in authoring data-driven tutorial dialogue system behavior and in investigating the effectiveness of human tutoring. Keywords: Tutorial dialogue, natural language, tutoring strategies. 1 ...