Personalizing robot tutors to individuals' learning differences

摘要: In education research, there is a widely-cited result called “Bloom’s two sigma” that characterizes the differences in learning outcomes between students who receive one-on-one tutoring and those traditional classroom instruction [1]. Tutored scored 95th percentile, or sigmas above mean, on average, compared to received instruction. human-robot interaction however, relatively little work exploring potential benefits of personalizing robot’s actions an individual’s strengths weaknesses. this study, participants solved grid-based logic puzzles with help personalized non-personalized robot tutor. Participants’ puzzle solving times were control conditions (n=80). Although personalizations less sophisticated than what human tutor can do, we still witnessed “one-sigma” improvement (68th percentile) post-tests treatment groups. We present these results as evidence even simple yield significant educational assistive interactions. Categories Subject Descriptors I.2.9 [Artificial Intelligence]: Robotics; J.4 [Computer Applications]: Social And Behavioral Sciences—Psychology General Terms Experimentation