The Influence of Learner Characteristics on Task-Oriented Tutorial Dialogue

Tutorial dialogue has been the subject of increasing attention in recent years, and it has become evident that empirical studies of human-human tutorial dialogue can contribute important insights to the design of computational models of dialogue. Students with particular characteristics may have specific dialogue profiles, and knowledge of such profiles could inform the design of tutorial dialogue systems whose strategies leverage the characteristics of the target population and address the communicative needs of those students. This paper reports on a study that was conducted to investigate the influence of learner characteristics (performance levels, self-efficacy, and gender) on the structure of task-oriented tutorial dialogue. A tutorial dialogue corpus was gathered from interactions transpiring in the course of problemsolving in a learning environment for introductory computer science. Analyses of the annotated dialogues suggest that the dialogue structure of (1) low-performing students differs significantly from that of highperforming students, (2) students with low self-efficacy differs significantly from that of students with high self-efficacy, and (3) males differs significantly from that of females.