TY - JOUR
T1 - Adaptive intelligent support to improve peer tutoring in algebra
AU - Walker, Erin
AU - Rummel, Nikol
AU - Koedinger, Kenneth R.
N1 - Funding Information:
Acknowledgments This work was supported by the Pittsburgh Science of Learning Center, NSF Grant #SBE-0836012, and a Computing Innovations Fellowship, NSF Grant #1019343. Thanks to Ruth Wylie for her comments and Sean Walker for his work on the assessment algorithm.
Publisher Copyright:
© International Artificial Intelligence in Education Society 2013.
PY - 2014/1
Y1 - 2014/1
N2 - Adaptive collaborative learning support (ACLS) involves collaborative learning environments that adapt their characteristics, and sometimes provide intelligent hints and feedback, to improve individual students' collaborative interactions. ACLS often involves a system that can automatically assess student dialogue, model effective and ineffective collaboration, and provide relevant support. While there is evidence that ACLS can improve student learning, little is known about why systems that incorporate ACLS are effective. Does relevant support improve student interactions by providing just-in-time feedback, or do students who believe they are receiving relevant support feel more accountable for the collaboration, and thus more motivated to improve their interactions? In this paper,we describe an adaptive system we have developed to support help-giving during peer tutoring in high school algebra: the Adaptive Peer Tutoring Assistant (APTA). To validate our approach, we conducted a controlled study that demonstrated that our system provided students with more relevant support and was more effective at improving student learning than parallel nonadaptive conditions. Our contributions involve generalizable techniques for implementing ACLS that can function adaptively and effectively, and the finding that adaptive support does indeed improve student learning because of the relevance of the support.
AB - Adaptive collaborative learning support (ACLS) involves collaborative learning environments that adapt their characteristics, and sometimes provide intelligent hints and feedback, to improve individual students' collaborative interactions. ACLS often involves a system that can automatically assess student dialogue, model effective and ineffective collaboration, and provide relevant support. While there is evidence that ACLS can improve student learning, little is known about why systems that incorporate ACLS are effective. Does relevant support improve student interactions by providing just-in-time feedback, or do students who believe they are receiving relevant support feel more accountable for the collaboration, and thus more motivated to improve their interactions? In this paper,we describe an adaptive system we have developed to support help-giving during peer tutoring in high school algebra: the Adaptive Peer Tutoring Assistant (APTA). To validate our approach, we conducted a controlled study that demonstrated that our system provided students with more relevant support and was more effective at improving student learning than parallel nonadaptive conditions. Our contributions involve generalizable techniques for implementing ACLS that can function adaptively and effectively, and the finding that adaptive support does indeed improve student learning because of the relevance of the support.
KW - Adaptive collaborative learning support
KW - Computer-supported collaborative learning
KW - Intelligent tutoring
KW - Peer tutoring
UR - http://www.scopus.com/inward/record.url?scp=84928407707&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84928407707&partnerID=8YFLogxK
U2 - 10.1007/s40593-013-0001-9
DO - 10.1007/s40593-013-0001-9
M3 - Article
AN - SCOPUS:84928407707
SN - 1560-4292
VL - 24
SP - 33
EP - 61
JO - International Journal of Artificial Intelligence in Education
JF - International Journal of Artificial Intelligence in Education
IS - 1
ER -