Modeling students’ knowledge is a fundamental part of intelligent
tutoring systems. One of the most popular methods for estimating
students’ knowledge is Corbett and Anderson’s 6 Bayesian Knowledge
Tracing model. The model uses four parameters per skill, fit using
student performance data, to relate performance to learning. Beck
1 showed that existing methods for determining these parameters
are prone to the Identifiability Problem: the same performance data
can be fit equally well by different parameters, with different implications
on system behavior. Beck offered a solution based on Dirichlet Priors
1, but, we show this solution is vulnerable to a different problem,
Model Degeneracy, where parameter values violate the model’s conceptual
meaning (such as a student being more likely to get a correct answer
if he/she does not know a skill than if he/she does).We offer a new
method for instantiating Bayesian Knowledge Tracing, using machine
learning to make contextual estimations of the probability that a
student has guessed or slipped. This method is no more prone to problems
with Identifiability than Beck’s solution, has less Model Degeneracy
than competing approaches, and fits student performance data better
than prior methods. Thus, it allows for more accurate and reliable
student modeling in ITSs that use knowledge tracing.
%0 Conference Paper
%1 Baker:2008:its
%A Baker, Ryan Shaun Joazeiro de
%A Corbett, Albert T.
%A Aleven, Vincent
%B ITS'08: Proc. 9th Int'l Conf. on Intelligent
Tutoring Systems
%C Montreal, Canada
%D 2008
%E Woolf, Beverley P.
%E Aïmeur, Esma
%E Nkambou, Roger
%E Lajoie, Susanne
%I Springer
%K imported thesis
%P 406--415
%R 10.1007/978-3-540-69132-7_44
%T More Accurate Student Modeling through Contextual Estimation of Slip
and Guess Probabilities in Bayesian Knowledge Tracing
%V 5091
%X Modeling students’ knowledge is a fundamental part of intelligent
tutoring systems. One of the most popular methods for estimating
students’ knowledge is Corbett and Anderson’s 6 Bayesian Knowledge
Tracing model. The model uses four parameters per skill, fit using
student performance data, to relate performance to learning. Beck
1 showed that existing methods for determining these parameters
are prone to the Identifiability Problem: the same performance data
can be fit equally well by different parameters, with different implications
on system behavior. Beck offered a solution based on Dirichlet Priors
1, but, we show this solution is vulnerable to a different problem,
Model Degeneracy, where parameter values violate the model’s conceptual
meaning (such as a student being more likely to get a correct answer
if he/she does not know a skill than if he/she does).We offer a new
method for instantiating Bayesian Knowledge Tracing, using machine
learning to make contextual estimations of the probability that a
student has guessed or slipped. This method is no more prone to problems
with Identifiability than Beck’s solution, has less Model Degeneracy
than competing approaches, and fits student performance data better
than prior methods. Thus, it allows for more accurate and reliable
student modeling in ITSs that use knowledge tracing.
%@ 978-3-540-69130-3
@inproceedings{Baker:2008:its,
abstract = {Modeling students’ knowledge is a fundamental part of intelligent
tutoring systems. One of the most popular methods for estimating
students’ knowledge is Corbett and Anderson’s [6] Bayesian Knowledge
Tracing model. The model uses four parameters per skill, fit using
student performance data, to relate performance to learning. Beck
[1] showed that existing methods for determining these parameters
are prone to the Identifiability Problem: the same performance data
can be fit equally well by different parameters, with different implications
on system behavior. Beck offered a solution based on Dirichlet Priors
[1], but, we show this solution is vulnerable to a different problem,
Model Degeneracy, where parameter values violate the model’s conceptual
meaning (such as a student being more likely to get a correct answer
if he/she does not know a skill than if he/she does).We offer a new
method for instantiating Bayesian Knowledge Tracing, using machine
learning to make contextual estimations of the probability that a
student has guessed or slipped. This method is no more prone to problems
with Identifiability than Beck’s solution, has less Model Degeneracy
than competing approaches, and fits student performance data better
than prior methods. Thus, it allows for more accurate and reliable
student modeling in ITSs that use knowledge tracing.},
added-at = {2017-03-16T11:50:55.000+0100},
address = {Montreal, Canada},
author = {Baker, Ryan Shaun Joazeiro{ }de and Corbett, Albert T. and Aleven, Vincent},
biburl = {https://www.bibsonomy.org/bibtex/232764ced2941bbd5852f04c86db63e84/krevelen},
booktitle = {ITS'08: Proc. 9th Int'l Conf. on Intelligent
Tutoring Systems},
crossref = {its:2008},
doi = {10.1007/978-3-540-69132-7_44},
editor = {Woolf, Beverley P. and A\"imeur, Esma and Nkambou, Roger and Lajoie, Susanne},
interhash = {bcda5cad5373462190a35e4f8973f325},
intrahash = {32764ced2941bbd5852f04c86db63e84},
isbn = {978-3-540-69130-3},
keywords = {imported thesis},
owner = {Rick},
pages = {406--415},
publisher = {Springer},
series = {LNCS},
timestamp = {2017-03-16T11:54:14.000+0100},
title = {More Accurate Student Modeling through Contextual Estimation of Slip
and Guess Probabilities in Bayesian Knowledge Tracing},
volume = 5091,
year = 2008
}