Bayesian networks: A teacher’s view (original) (raw)
Related papers
The Eurasia Proceedings of Educational and Social Sciences, 2022
The development and multiple variations in technology and science have endured the education. Nevertheless, education is one of the primary components that uphold the development of a country. In the meantime, diverse technologies have been introduced to blend in education. For example, Bayesian Networks is a probability-based data modelling approach that illustrates a set of variables and their conditional dependencies through a Directed Acyclic Graph (DAG). Each node formed inside the graph has a Conditional Probability Table (CPT). Therefore, the endurance of this bibliometric review is to identify peer-reviewed literature on the Bayesian network approach in education. Scopus citation databases are used in the data-gathering phase. In addition, PICOS Framework and PRISMA approach were obtained and analysed for keyword search on the research topic. This bibliographic data of articles published in the journals over ten years were extracted. R-tool and VOS viewer were used to analyse the data contained in all journals and articles. This bibliometric review shows the usage of the Bayesian network approach in education, especially in educational application development. The findings from 87 articles extracted show that teaching and learning activity delivery and educational management have improved. The findings show an increasing trend in published studies related to the Bayesian network in education. Next, the United Kingdom and the United States became highly productive countries in the publication of studies within the scope of the Bayesian network. Next, interdisciplinary became the primary choice in the publication of studies in the field of Bayesian networks. The level of predictive accuracy generated through the Bayesian network approach improves the quality of educational application development. However, the findings of previous studies indicate that there is a need to extend the Bayesian network approach in education.
Using Bayesian Networks to Manage Uncertainty in Student Modeling
User Modeling and User-adapted Interaction, 2002
When a tutoring system aims to provide students with interactive help, it needs to know what knowledge the student has and what goals the student is currently trying to achieve. That is, it must do both assessment and plan recognition. These modeling tasks involve a high level of uncertainty when students are allowed to follow various lines of reasoning and are not required to show all their reasoning explicitly. We use Bayesian networks as a comprehensive, sound formalism to handle this uncertainty. Using Bayesian networks, we have devised the probabilistic student models for Andes, a tutoring system for Newtonian physics whose philosophy is to maximize student initiative and freedom during the pedagogical interaction. Andes’ models provide long-term knowledge assessment, plan recognition, and prediction of students’ actions during problem solving, as well as assessment of students’ knowledge and understanding as students read and explain worked out examples. In this paper, we describe the basic mechanisms that allow Andes’ student models to soundly perform assessment and plan recognition, as well as the Bayesian network solutions to issues that arose in scaling up the model to a full-scale, field evaluated application. We also summarize the results of several evaluations of Andes which provide evidence on the accuracy of its student models.
Teaching Grown-ups how to use Bayesian Networks
A Bayesian network, or directed acyclic graphical model is a probabilistic graphical model that represents conditional dependencies and conditional independencies of a set of random variables. Each node is associated with a probability function that takes as input a particular set of values for the node’s parent variables and gives the probability of the variable represented by the node, conditioned on the values of its parent nodes. Links represent probabilistic dependencies, while the absence of a link between two nodes denotes a conditional independence between them. Bayesian networks can be updated by means of Bayes’ Theorem. Because Bayesian networks are a powerful representational and computational tool for probabilistic inference, it makes sense to instruct young grownups on their use and even provide familiarity with software packages like Netica. We present introductory schemes with a variety of examples.
Developing a Pedagogical Intervention Support based on Bayesian Networks
2017
This paper proposes an approach for developing pedagogical interventions support in information technologies for education based on Bayesian networks. In this paper, we show how the presented approach is able to automate pedagogical interventions in Model-tracing cognitive tutors (MTCTs). The paper discusses a novel Bayesian network topology to assess student’s mastery to provide pedagogical interventions. Preliminary results to assess effectiveness of the proposed approach were obtained by implementing it in a MTCT called TITUS.
Bayesian networks for student model engineering
Computers & Education, 2010
Bayesian networks are graphical modeling tools that have been proven very powerful in a variety of application contexts. The purpose of this paper is to provide education practitioners with the background and examples needed to understand Bayesian networks and use them to design and implement student models. The student model is the key component of any adaptive tutoring system, as it stores all the information about the student (for example, knowledge, interest, learning styles, etc.) so the tutoring system can use this information to provide personalized instruction. Basic and advanced concepts and techniques are introduced and applied in the context of typical student modeling problems. A repertoire of models of varying complexity is discussed. To illustrate the proposed methodology a Bayesian Student Model for the Simplex algorithm is developed.
A Bayesian Network Approach To Modeling Learning Progressions
Learning Progressions in Science, 2012
A central challenge in using learning progressions (LPs) in practice is modeling the relationships that link student performance on assessment tasks to students' levels on the LP. On the one hand, there is a progression of theoretically defined levels, each defined by a configuration of knowledge, skills, and/or abilities (KSAs). On the other hand, there are observed performances on assessment tasks, associated with levels but only imperfectly and subject to inconsistencies. What is needed is a methodology that can be used to map assessment performance onto the levels, to combine information across multiple tasks measuring similar and related KSAs, to support inferences about students, and to study how well actual data exhibit the relationships posited by the LP. In terms of the "assessment triangle" proposed by the National Research Council's Committee on the Foundations of Assessment (National Research Council [NRC], 2001), coherent theoretical and empirical connections are needed among the theory embodied in a progression (cognition), the tasks that provide observable evidence about a student's understanding relative to that progression (observation), and the analytic models that characterize the relationship between them (interpretation). This chapter discusses the use of Bayesian inference networks, or Bayes nets for short, to model LPs. Bayes nets are a class of statistical models that have been adapted for use in educational measurement. At present, the use of Bayes nets in LP contexts is in its relative infancy. We describe the fundamentals of the approach and the challenges we faced applying it in an application involving a LP in beginning computer network engineering. The first section of the chapter reviews our framework of model-based reasoning. Subsequent sections map the development of LPs and associated assessments onto this framework and show how Bayes nets are used to manage the problems of evidence and uncertainty in the relationship between LPs and assessment task performances. We then explain in more detail what Bayes nets are, how they can be used to model task performance in the context of LPs, and the challenges that we face in this work. MODEL-BASED REASONING The lens of model-based reasoning helps clarify the role Bayes nets can play in modeling LPs. A model is a simplified representation focused on certain aspects of Revision NC: about stu provides using thi Learning LPs are understa (Corcora between compute of router LPs (Co that are d dimensio stages th A BAYESIAN N
Using Fine-Grained Skill Models to Fit Student Performance with Bayesian Networks
Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, 2010
The ASSISTment online tutoring system was used by over 600 students during the school year [2004][2005]. Each student used the system as part of their math classes 1-2 times a month, doing on average over 100+ state-test items, and getting tutored on the ones they got incorrect. The ASSISTment system has 4 different skill models, each at different grain-size involving 1, 5, 39 or 106 skills. Our goal in the paper is to develop a model that will predict whether a student will get correct a given item. We compared the performance of these models on their ability to predict a student state test score, after the state test was "tagged" with skills for the 4 models. The best fitting model was the 39 skill model, suggesting that using finer-grained skills models is useful to a point. This result is pretty much the same as that which was achieved by Feng, Heffernan, Mani, & Heffernan (in press), who were working simultaneously, but using mized-effect models instead of Bayes networks. We discuss reasons why the finest-grained model might not have been able to predict the data the best. Implications for large scale testing are discussed.
Inspecting and Visualizing Distributed Bayesian Student Models
2000
Bayesian Belief Networks provide a principled, mathematically sound, and logically rational mechanism to represent student models. The belief net backbone structure proposed by Reye [14,15] offers a practical way to represent and update Bayesian student models describing both cognitive and social aspects of the learner. Considering students as active participants in the modelling process, this paper explores visualization and inspectability issues of Bayesian student modelling. This paper also presents ViSMod an integrated tool to visualize and inspect distributed Bayesian student models.
Dynamic Bayesian Networks in Educational Measurement: Reviewing and Advancing the State of the Field
Applied Measurement in Education, 2018
As the popularity of rich assessment scenarios increases so must the availability of psychometric models capable of handling the resulting data. Dynamic Bayesian networks (DBNs) offer a fast, flexible option for characterizing student ability across time under psychometrically complex conditions. In this article, a brief introduction to DBNs is offered, followed by a review of the existing literature on the use of DBNs in educational and psychological measurement with a focus on methodological investigations and novel applications that may provide guidance for practitioners wishing to deploy these models. The article concludes with a discussion of future directions for research in the field.
Using Bayesian networks to improve knowledge assessment
Computers & Education, 2013
In this paper, we describe the integration and evaluation of an existing generic Bayesian student model (GBSM) into an existing computerized testing system within the Mathematics Education Project (PmatE-Projecto Matemática Ensino) of the University of Aveiro. This generic Bayesian student model was previously evaluated with simulated students, but a real application was still missing. In the work presented here, we have used the GBSM to define Bayesian Student Models (BSMs) for a concrete domain: first degree equations. In order to test the diagnosis capabilities of such BSMs, an evaluation with 152 students has been performed. Each of the 152 students took both a computerized test within PMatE and a written exam, both of them designed to measure students knowledge in 12 concepts related to first degree equations. The written exam was graded by three experts. Then two BSMs were developed, one for the computer test and another one for the written exam. These BSMs were used to to obtain estimations of student's knowledge on the same 12 concepts, and the inter-rater agreement among the different measures was computed. Results show a high degree of agreement among the scores given by the experts and also among the diagnosis provided by the BSM in the written exam and the experts average, but a low degree of agreement among the diagnosis provided by the BSM in the computer test and expert's average.