EXP: Helping Teachers Help Their Students: Teachers’ Use of Intelligent Tutoring Software Analytics to Improve Student Learning.

PIs: Vincent Aleven, Bruce McLaren
Carnegie-Mellon University
Award Details

Improving learning in K-12 Science, Technology, Engineering, and Mathematics (STEM) is a critical national need as more jobs require STEM proficiency. Recently, Intelligent Tutoring Systems (ITSs) have shown great promise in improving STEM learning in middle school and high school. While these tutors support students directly, they do not provide information to teachers. This project will remedy this shortcoming by developing software that will display the students’ progress in middle school mathematics and will also suggest help that the teacher can provide to the students to enhance their learning. The help that the software provides is based on the analysis of learning built into the tutor, but which is too complex to be usable by teachers.

This project will take a user-centered design approach to create a teacher’s dashboard for ITSs, so that it can be effective in various realistic classroom scenarios. Classroom studies will be conducted to evaluate whether, when used by the teacher, the dashboard helps students learn more effectively. The work will focus on Mathtutor, a freely available website with intelligent tutoring software for middle-school mathematics learning. Specifically, the project will focus on Lynnette, a tutor for grades 7 and 8 with a proven track record in helping students learn to solve linear equations. The research questions to be addressed include: What is the up-to-the-minute data about student learning that intelligent tutoring systems can provide that is helpful to teachers and how can it best be presented in an actionable manner? How do teachers use actionable analytics presented in a dashboard to help their students? Do students learn better when their teacher monitors a dashboard and uses it to adjust the instruction?

The project work will include design, development, pilot testing, and classroom studies. The dashboard will be designed with substantial teacher input. Further, the project will provide teacher guides for how to use the dashboard via the Mathtutor website. The dashboard will work with all Mathtutor units and all tutors built with CTAT/Tutorshop, a widely used tutor-building infrastructure. Diverse student groups will benefit, as tutoring software has been effective with a wide range of students, including minority students, non-native English speakers, and low-income students.