Learning by Teaching SimStudent – An Initial Classroom Baseline Study comparing with Cognitive Tutor


Noboru Matsuda, Evelyn Yarzebinski, Victoria Keiser, Rohan Raizada, Gabriel Stylianides, William W. Cohen and Kenneth R. Koedinger

Paper type: 
Full paper
5. 10:30-11:30, Thursday 30 June


This paper describes an application of a machine-learning agent, SimStudent, as a teachable peer learner that allows a student to learn by teaching. SimStudent has been integrated into APLUS (Artificial Peer Learning environment Using SimStudent), an on-line game-like learning environment. The first classroom study was conducted in local public high schools to test the effectiveness of APLUS for learning linear algebra equations. In the study, learning by teaching (i.e., APLUS) was compared with learning by tutored-problem solving (i.e., Cognitive Tutor). The results show that the prior knowledge has a strong influence on tutor learning – for students with insufficient training on the target problems, learning by teaching may have limited benefits compared to learning by tutored problem solving. It was also found that students often use inappropriate problems to tutor SimStudent that did not effectively facilitate the tutor learning.


Learning by teaching, teachable agent, SimStudent, machine learning, inductive logic programming