Limitations of Student Control: Do Students Know When They Need Help?
ITS '00 Proceedings of the 5th International Conference on Intelligent Tutoring Systems
An Intelligent SQL Tutor on the Web
International Journal of Artificial Intelligence in Education
On Using Learning Curves to Evaluate ITS
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
Detecting when students game the system, across tutor subjects and classroom cohorts
UM'05 Proceedings of the 10th international conference on User Modeling
Adapting to when students game an intelligent tutoring system
ITS'06 Proceedings of the 8th international conference on Intelligent Tutoring Systems
Detecting gaming the system in constraint-based tutors
UMAP'10 Proceedings of the 18th international conference on User Modeling, Adaptation, and Personalization
Hi-index | 0.00 |
We examined high-level help (HLH) seeking behaviour of students by data mining in SQL-Tutor. Students who used HLH very frequently had the lowest learning rate; their learning was also shallow. They attempted very difficult problems compared to other groups but only solved very easy problems, suggesting that they were usually situated well beyond their Zone of Proximal Development. They also abandoned a large number of problems without solving them. Manual inspection of the logs showed erratic problem solving behaviour, suggesting a "guess and copy" strategy.The group of students who used HLH very infrequently seemed to contain two distinct sub-groups: students with high expertise, and students with very low expertise who still did not use HLH. Learning rates were highest for students who used moderate HLH. Students with lower usage of HLH solved the most difficult problems comparatively, without the use of HLH, and had high learning rates, suggesting the ITS is most beneficial for this group of students.