Rus, Vasile (The University of Memphis) | Maharjan, Nabin (The University of Memphis) | Tamang, Lasang Jimba (The University of Memphis) | Yudelson, Michael (Carnegie Learning Inc.) | Berman, Susan (Carnegie Learning Inc.) | Fancsali, Stephen E. (Carnegie Learning Inc.) | Ritter, Steve (Carnegie Learning Inc.)
Understanding effective human tutors’ strategies is one approach to discovering effective tutorial strategies. These strategies are described in terms of actions that tutors take while interacting with learners. To this end, we analyze in this paper dialogue-based interactions between professional tutors and tutees. There are two challenges when exploring patterns in such dialogue-based tutorial interactions. First, we need to map utterances, by the tutor and by the tutee, into actions. To address this challenge, we rely on the language-as-action theory according to which when we say something we do something. A second challenge is detecting effective tutorial sessions using objective measurements of learning. To tackle this challenge we align tutorial conversations with pre- and post- measures of student mastery obtained from an intelligent tutoring system with which the students interacted before and after interacting with the human tutor.
We examine a corpus of reflective tutorial dialogues between human tutor and student after the student completed introductory physics problems, to predict when the tutor abstracted from the student's preceding turn or when the tutor specialized from the student's preceding turn. Tutor abstraction occurs when the tutor repeats a segment of the student's turn using more general terms. Tutor specialization occurs when the tutor repeats a segment of the student's turn using more concrete terms. We find that features extracted from the reflective dialogue context produce the most predictive models. Also, the tutor abstracts more often when the student shows signs of working at a very detailed level for awhile, and prompts for specification when the student's responses are imprecise.
Mitchell, Christopher Michael (North Carolina State University) | Ha, Eun Young (North Carolina State University) | Boyer, Kristy Elizabeth (North Carolina State University) | Lester, James C. (North Carolina State University)
One-on-one tutoring is significantly more effective than traditional classroom instruction. In recent years, automated tutoring systems are approaching that level of effectiveness by engaging students in rich natural language dialogue that contributes to learning. A promising approach for further improving the effectiveness of tutorial dialogue systems is to model the differential effectiveness of tutorial strategies, identifying which dialogue moves or combinations of dialogue moves are associated with learning. It is also important to model the ways in which experienced tutors adapt to learner characteristics. This paper takes a corpus- based approach to these modeling tasks, presenting the results of a study in which task-oriented, textual tutorial dialogue was collected from remote one-on-one human tutoring sessions. The data reveal patterns of dialogue moves that are correlated with learning, and can directly inform the design of student-adaptive tutorial dialogue management systems.
These tutors integrate two independent but related strands of research: intelligent tutoring systems and task-oriented dialogue systems. While the tutors share a core approach to teactfing procedural tasks, each was designed to explore a different set of issues. This paper outlines the issues that arise in taskoriented tutorial dialogue and the ways they have been addressed in these four tutors.
The CIRCSIM-Tutor intelligent tutoring system project has been built on the basis of numerous studies of transcripts of expert human tutors (professors) teaching first year medical students. We also have transcripts of novice tutors (second year medical students) teaching the same material to medical students at the same level. In this paper we identify measurable differences in the teaching styles between the novices and experts. Examples of tutoring of identical topics were isolated from the novice-and expert-tutored transcripts and various dialogue acts were counted. The primary result is that expert tutors are more likely than novice tutors to query students for information as opposed to informing them directly.