In this study we investigated students’ conversations with a virtual science tutor, either individually or in small groups. Students were presented with narrated multimedia science problems and explanations, followed by question-answer dialogs with the virtual tutor. Students who received one-on-one and small group tutoring received the same set of multimedia presentations questions posed by the virtual tutor. Students in the small group condition discussed their answer before one of the students responded to the tutor. We asked if students receiving computerized tutoring in groups would achieve learning gains equivalent to students receiving one-on-one tutoring, and if both groups would demonstrate greater learning gains from pretest to posttest than students in business-as-usual classrooms. One hundred eighty-three (183) students (in 13 classrooms) at 4 schools participated in the study. Of the 183 students, 114 were randomly assigned to the experimental condition with group discussions and Marni and 69 were received individual tutoring with Marni. When compared with the control group, effect sizes for were d = 0.48 for the Group condition and d = -0.51 for the Individual condition. A two-way ANOVA suggested a main effect for tutoring group, F = 16.8, df (4,1171), p < .0001. In general, students reported benefiting from listening to one another, and the small group interactions, even though they sometimes did not agree with the group answer. We conclude our findings with a vision for a next generation of science tutoring using technology to help all students learn science using technology.
Keywords: virtual, tutoring, intelligent, learning, student, multimedia