Bayesian Student Models Based on Item to Item Knowledge Structures

Abstract

Abstract. Bayesian networks are commonly used in cognitive student modeling and assessment. They typically represent the item-concepts relationships, where items are observable responses to questions or exercises and concepts represent latent traits and skills. Bayesian networks can also represent concepts-concepts and concepts-misconceptions relationships. We explore their use for modeling item-item relationships, in accordance with the theory of knowledge spaces. We compare two Bayesian frameworks for that purpose, a standard Bayesian network approach and a more constrained framework that relies on a local independence assumption. Their performance is compared over their respective ability to predict item outcome and through simulations over two data sets. The simulation results show that both approaches can effectively perform accurate predictions, but the constrained approach shows higher predictive power than a Bayesian Network. We discuss the applications of item to item structure for cognitive modeling within different contexts.

An application of Bayesian inference to examine student retention and attrition in the STEM classroom

“…This has been the primary focus and application of Bayesian methods in education thus far. Indeed, most studies employing Bayesian methods have used them to perform psychometric and factor analyses of novel assessment types (e.g., multi-skill itemized activities and question types) and surveys to study student comprehension, cognition, and attitudes toward learning (Desmarais and Gagnon, 2006;Pardos et al, 2008;Brassil and Couch, 2019;Martinez, 2021;Parkin and Wang, 2021;Vaziri et al, 2021;Wang et al, 2021). The insights obtained from these studies have led to the design, development, and deployment of more adaptive learning and student-focused knowledge assessment content, based on their aptitude levels, allowing educators to learn more about student comprehension and how individualized content can be tailored to students (Drigas et al, 2009).…”

Predicting Students’ Academic Performances – A Learning Analytics Approach using Multiple Linear Regression

“…Bayesian networks have also been used to model two different approaches to determine the probability a multi skill question has of being correct [15] and to predict future group performance in face-to-face collaborative learning [16]. It has also been used to predict end-of-year exam performance through student activity with online tutors [17] and to predict item response outcome [18]. Different types of neural network models have been used in prediction as well.…”

Decade review (1999-2009): progress of application of artificial intelligence tools in student diagnosis

“…The system went through an initial testing with very satisfying success rate and it was also successfully tested through an actual e-learning application called Multitutor (Sevarac, 2006). Desmarais and Gagnon (2006) explored the use of two Bayesian frameworks (of one typical Bayesian network and of a constrained version under the assumption of local independence) in an attempt to predict item outcome. The two approaches were compared over their predictive power and their performance was measured using data from real tests to conduct simulations.…”

“…After the choice of an item, the result of the answer, whether it is a success or a failure, is fed to the inference algorithm. Although both methods turn out to give accurate predictions, the constrained one obtains better predictive results (Desmarais and Gagnon, 2006). Wei and Blank (2006) conducted an experiment in order to study the sufficiency of atomic Bayesian networks for student models.…”