More Accurate Student Modeling through Contextual Estimation of Slip and Guess Probabilities in Bayesian Knowledge Tracing

By Ryan Shaun Joazeiro de Baker, Albert T. Corbett, Vincent A. W. M. M. Aleven. International Conference on Intelligent Tutoring Systems, 2008

514 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/c4981ff9ba7e06c5c312328ffaa4184cbaea6825

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

Citations in the corpus

Enhancing the prediction of student performance based on the machine learning XGBoost algorithm (2021, methodology): “For instance, the original version has been adopted through the identification of student guessing and slipping factors related to his prior knowledge (Baker et al., 2008).”
Individualized Bayesian Knowledge Tracing Models (2013, methodology): “BKT models are usually fit using the expectation maximization method (EM) [2], Conjugate Gradient Search [1], or discretized brute-force search [7].”
Dynamic Key-Value Memory Networks for Knowledge Tracing (2016, background): “Many following variations were raised by integrating personalization study [19, 33], exercise diversity [20], and other information [4, 23] into the Bayesian framework.”
Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing (2010, methodology): “More recent work by Baker et al [4] has found utility in the contextualization of the guess and slip parameters using a multi-staged machine-learning processes that also uses regression to fine tune parameter values.”
Knowledge Tracing: A Survey (2022, methodology): “Further work has been done through incorporating factors that reflect the characteristics of individual students [28, 84], or the characteristics of specific items of assessment within skills [85].”
Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing (2020, background): “ude Bayesian Knowledge Tracing (BKT) [3], Collaborative Filtering (CF) [20,11] and many others. BKT is a classical, prominent approach to knowledge tracing that has been studied extensively over time [3,4,23,17,15,16,21,18,9,19]. BKT represents a student’s knowledge state as a tuple of binary values”
Multi-Armed Bandits for Intelligent Tutoring Systems (2013, methodology): “For this model, many approaches rely on Knowledge Tracing methods (Corbett and Anderson, 1994), or variants, and some methods already try to estimate those parameters form data (González-Brenes and Mostow, 2012; Baker et al., 2008; González-Brenes et al., 2014; Dhanani et al., 2014).”
A review of recent advances in learner and skill modeling in intelligent learning environments (2012, background): “correctly answers an item by chance, are important sources of uncertainty (Baker and Corbett 2008).”