When do Students Interrupt Help? Effects of Time, Help Type, and Individual Differences

Authors:
Cecily Heiner;Joseph Beck;Jack Mostow
Affiliations:
Carnegie Mellon University, Project LISTEN, Newell Simon Hall, 5000 Forbes Avenue Pittsburgh, PA 15213;Carnegie Mellon University, Project LISTEN, Newell Simon Hall, 5000 Forbes Avenue Pittsburgh, PA 15213;Carnegie Mellon University, Project LISTEN, Newell Simon Hall, 5000 Forbes Avenue Pittsburgh, PA 15213
Venue:
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
Year:
2005

Citing 6
Cited 2

Help seeking, learning and contingent tutoring

Computers & Education
Evaluating tutors that listen: an overview of project LISTEN

Smart machines in education
Limitations of Student Control: Do Students Know When They Need Help?

ITS '00 Proceedings of the 5th International Conference on Intelligent Tutoring Systems
Learning and reasoning about interruption

Proceedings of the 5th international conference on Multimodal interfaces
Off-task behavior in the cognitive tutor classroom: when students "game the system"

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Predicting student help-request behavior in an intelligent tutor for reading

UM'03 Proceedings of the 9th international conference on User modeling

Some useful tactics to modify, map and mine data from intelligent tutors

Natural Language Engineering
Motivationally Intelligent Systems: Diagnosis and Feedback

Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work

Quantified Score

Hi-index	0.00

Visualization

Abstract

When do students interrupt help to request different help? To study this question, we embedded a within-subject experiment in the 2003-2004 version of Project LISTEN's Reading Tutor. We analyze 168,983 trials of this experiment, randomized by help type, and report patterns in when students choose to interrupt help. Using the amount of prior help, we fit an exponential curve to predict interruption rate with an r2 of 0.97 on aggregate data and an r2 of 0.22 on individual data. To improve the model fit for individual data, we adjust our model to account for different types of help and individual differences. Finally, we report small but significant correlations between a student parameter in our model and external measures of motivation and academic performance.