Lessons from Project LISTEN’s Session Browser
Jack Mostow, Joseph E. Beck, Andrew Cuneo, Evandro Bacci Gouvêa, Cecily Heiner, Octavio Juarez · 2010
Intelligent tutoring systems’ ability to log their interactions with students poses both an opportunity and a challenge. Compared to human observation of live or videotaped tutoring, such logs can be more extensive in the number of students, more comprehensive in the number of sessions, and more exquisite in the level of detail. They avoid observer effects, cost less, and are easier to analyze. The resulting data is a potential gold mine [4]—but mining it requires the right tools to locate promising areas, obtain samples, and analyze them.