Does Supporting Multiple Student Strategies in Intelligent Tutoring Systems Lead to Better Learning?

Abstract

One feature that makes an Intelligent Tutoring System (ITS) hard to build is strategy freedom, where students are able to pursue multiple solution strategies within a given problem.. But does greater freedom mean that students learn more robustly?  We developed three versions of the same ITS for solving linear equations that differed only in the amount of freedom. We conducted a study in two US middle schools with 57 students in grades 7 and 8. Overall, students’ algebra skills improved. There was no difference in learning gain and motivation between the conditions. Students tended to adhere to a standard strategy and its minor variations, and not pursue alternative strategies. Thus, the study suggests that in early algebra learning, a small amount of freedom is useful, validating, although to a limited degree, one source of complexity in ITS architectures.