Dialogue-Learning Correlations in Spoken Dialogue Tutoring

We examine correlations between dialogue characteristics and learning in two corpora of spoken tutoring dialogues: a human-human corpus and a humancomputer corpus, both of which have been manually annotated with dialogue acts relative to the tutoring domain. The results from our human-computer corpus show that the presence of student utterances that display reasoning, as well as the presence of reasoning questions asked by the computer tutor, both positively correlate with learning. The results from our human-human corpus show that the introduction of a new concept into the dialogue by students positively correlates with learning, but student attempts at deeper reasoning do not, and the human tutor’s attempts to direct the dialogue negatively correlate with learning.

• Type: Conference
• Year: 2005
• Where: AIED
• Authors: Katherine Forbes-Riley, Diane J. Litman, Alison Huettner, Arthur Ward
• Keywords: AIED 2005, Artificial Intelligence, Dialogue, Dialogue Characteristics, Human-human Corpus