Paper Info
Title
Learning by teaching SimStudent: an initial classroom baseline study comparing with cognitive tutor
Abstract
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.
Year
DOI
Venue
2011
10.1007/978-3-642-21869-9_29
AIED
Keywords
Field
DocType
linear algebra equation,tutor learning,machine-learning agent,insufficient training,local public high school,inappropriate problem,limited benefit,cognitive tutor,initial classroom baseline study,classroom study,artificial peer learning environment
Inductive logic programming,Experiential learning,TUTOR,Computer science,Cognitive tutor,Knowledge management,Learning environment,Peer learning,Error-driven learning,Multimedia,Learning by teaching
Conference
Volume
ISSN
Citations 
6738
0302-9743
15
PageRank 
References 
Authors
1.55
4
7
Name
Order
Citations
PageRank
Noboru Matsuda120023.45
Evelyn Yarzebinski2588.24
Victoria Keiser3566.32
Rohan Raizada4555.85
Gabriel Stylianides5586.73
William W. Cohen6101781243.74
Kenneth R. Koedinger73551403.07