Cognitive Computer Tutors: Solving the Two-Sigma Problem
UM '01 Proceedings of the 8th International Conference on User Modeling 2001
Identifiability: A Fundamental Problem of Student Modeling
UM '07 Proceedings of the 11th international conference on User Modeling
ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
Does Help Help? Introducing the Bayesian Evaluation and Assessment Methodology
ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
ITS '08 Proceedings of the 9th international conference on Intelligent Tutoring Systems
Inferring learning and attitudes from a Bayesian Network of log file data
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
Blending Assessment and Instructional Assisting
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
Addressing the assessment challenge with an online system that tutors as it assesses
User Modeling and User-Adapted Interaction
The Impact of Off-task and Gaming Behaviors on Learning: Immediate or Aggregate?
Proceedings of the 2009 conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling
Performance Factors Analysis --A New Alternative to Knowledge Tracing
Proceedings of the 2009 conference on Artificial Intelligence in Education: Building Learning Systems that Care: From Knowledge Representation to Affective Modelling
Predicting student help-request behavior in an intelligent tutor for reading
UM'03 Proceedings of the 9th international conference on User modeling
Modeling individualization in a bayesian networks implementation of knowledge tracing
UMAP'10 Proceedings of the 18th international conference on User Modeling, Adaptation, and Personalization
ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part I
The fine-grained impact of gaming (?) on learning
ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part I
A bayes net toolkit for student modeling in intelligent tutoring systems
ITS'06 Proceedings of the 8th international conference on Intelligent Tutoring Systems
Learning factors analysis – a general method for cognitive model evaluation and improvement
ITS'06 Proceedings of the 8th international conference on Intelligent Tutoring Systems
Looking beyond transfer models: finding other sources of power for student models
UMAP'11 Proceedings of the 19th international conference on User modeling, adaption, and personalization
Learning what works in its from non-traditional randomized controlled trial data
International Journal of Artificial Intelligence in Education - Special issue on Best of ITS 2010
Modeling multiple distributions of student performances to improve predictive accuracy
UMAP'12 Proceedings of the 20th international conference on User Modeling, Adaptation, and Personalization
| Hi-index | 0.00 |
Student modeling is a fundamental concept applicable to a variety of intelligent tutoring systems (ITS). However, there is not a lot of practical guidance on how to construct and train such models. This paper compares two approaches for student modeling, Knowledge Tracing (KT) and Perlbrmance Factors Analysis (PFA), by evaluating their predictive accuracy on individual student practice opportunities. We explore the space of design decisions for each approach and find a set of "best practices" for each. In a head to head comparison, we find that PFA has considerably higher predictive accuracy than KT. In addition to being more accurate, we lbund that PFA's parameter estimates were more plausible. Our best-performing model was a variant of PFA that ignored the tutor's transfer model; that is, it assumed all skills influenced performance on all problems. One possible implication is that this result is a general one suggesting there is benefit from considering models that incorporate information from more than the typical handful of skills associated with a problem in the transfer model. Alternately, an explanation for this result is the transfer model that our tutor uses is particularly weak. We also found that both KT and PFA have relatively low predictive accuracy for cases where students generate incorrect responses, and 2/3 of the model's errors are false positives, indicating a better means of determining when students will make mistakes is needed.