Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Learning from Data
Conclusions
References
All Topics
Computer Science
Machine Learning

Bayesian networks for student model engineering

Profile image of Eva MillánEva Millán

2010, Computers & Education

https://doi.org/10.1016/J.COMPEDU.2010.07.010
visibility

…

description

22 pages

link

1 file

Abstract

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.

Figures (21)
Fig. 2. A step-by-step modeling of the sneezing example.
Fig. 2. A step-by-step modeling of the sneezing example.
Prior probability distribution is an unconditional distribution that does not change, no matter the observations we make. Cat is one of the two root nodes, in our example network. We obtain the probability distribution for that node by answering a question “how likely is a couple (like Paul and Susan) to have a cat? ” The answer will be a number between 0 and 1 (or between 0 and 100%, which can later be transformed into a probability by dividing it by a 100). Let us take a guess that about 20% of couples own cats. Therefore, we arrive at the probability of 0.2 that Paul and Susan have a cat.
Prior probability distribution is an unconditional distribution that does not change, no matter the observations we make. Cat is one of the two root nodes, in our example network. We obtain the probability distribution for that node by answering a question “how likely is a couple (like Paul and Susan) to have a cat? ” The answer will be a number between 0 and 1 (or between 0 and 100%, which can later be transformed into a probability by dividing it by a 100). Let us take a guess that about 20% of couples own cats. Therefore, we arrive at the probability of 0.2 that Paul and Susan have a cat.
Fig. 4. A Bayesian network equivalent to the one for the sneezing example from Fig. 2(e), but with all arcs reversed. Sneezing is very unlikely to happen in the absence of both the factors (0.01). Furthermore, Rhinitis has a slightly higher chance of causing Sneezing than does Cold (0.9 versus 0.85). When both factors are present, Sneezing is bound to occur (0.99). Two of the probabilities above are quite extreme. Despite that, they still leave some room for uncertainty. For example, John will be Sneezing, on average, in one out of a 100 situations when he has not caught Cold and was not having Rhinitis. Assigning probabilities of 0 o1
Fig. 4. A Bayesian network equivalent to the one for the sneezing example from Fig. 2(e), but with all arcs reversed. Sneezing is very unlikely to happen in the absence of both the factors (0.01). Furthermore, Rhinitis has a slightly higher chance of causing Sneezing than does Cold (0.9 versus 0.85). When both factors are present, Sneezing is bound to occur (0.99). Two of the probabilities above are quite extreme. Despite that, they still leave some room for uncertainty. For example, John will be Sneezing, on average, in one out of a 100 situations when he has not caught Cold and was not having Rhinitis. Assigning probabilities of 0 o1
Fig. 5. The sneezing example model with parameters.
Fig. 5. The sneezing example model with parameters.
Fig. 6. Possible configurations of three adjacent variables in a Bayesian network. BE EE A Ee ne ne ey SA eS SAE eS SRE Ie ROSAS we EMO eT UN CS Re ANS SEES ST Sen MU oe we Fel AER RT Ne AN eK CONES oes meee ee RLS ee. Neen ewe ge However, variables can be connected through other variables. The notion of conditional independence is at the center of cases like that. Fig. 6 shows the possible configurations of three adjacent variables that can be found in a BN. In the chain configuration (also called linear or serial), A and C are dependent if we do not know which state B is in. Once we know the state of B, A and C become independent. The state of Cis influenced only by the state of B, and no change in A is carried over to C. We say that C is independent of A given B. In the sneezing example, achain is formed by Allergies, Rhinitis, and Sneezing. If we do not know whether or not John is having Rhinitis, knowing whether or not he has Allergies influences our belief about him Sneezing. Ifhe has Allergies, probability of Sneezing is higher; if he has not, it is lower. However, once we know that John is not having Rhinitis whether or not he has Allergies becomes irrelevant from the point of view of Sneezing.
Fig. 6. Possible configurations of three adjacent variables in a Bayesian network. BE EE A Ee ne ne ey SA eS SAE eS SRE Ie ROSAS we EMO eT UN CS Re ANS SEES ST Sen MU oe we Fel AER RT Ne AN eK CONES oes meee ee RLS ee. Neen ewe ge However, variables can be connected through other variables. The notion of conditional independence is at the center of cases like that. Fig. 6 shows the possible configurations of three adjacent variables that can be found in a BN. In the chain configuration (also called linear or serial), A and C are dependent if we do not know which state B is in. Once we know the state of B, A and C become independent. The state of Cis influenced only by the state of B, and no change in A is carried over to C. We say that C is independent of A given B. In the sneezing example, achain is formed by Allergies, Rhinitis, and Sneezing. If we do not know whether or not John is having Rhinitis, knowing whether or not he has Allergies influences our belief about him Sneezing. Ifhe has Allergies, probability of Sneezing is higher; if he has not, it is lower. However, once we know that John is not having Rhinitis whether or not he has Allergies becomes irrelevant from the point of view of Sneezing.
Fig. 7 shows the evolution of the model’s parameters as new evidence is introduced. The first step is the computation of all a prio. probabilities. This step is commonly called the initialization process, and its results are known as the initial state. Fig. 7. Probability distributions associated with variables in the sneezing example at different stages of inference.
Fig. 7 shows the evolution of the model’s parameters as new evidence is introduced. The first step is the computation of all a prio. probabilities. This step is commonly called the initialization process, and its results are known as the initial state. Fig. 7. Probability distributions associated with variables in the sneezing example at different stages of inference.
When John starts Sneezing the probabilities are updated to account for this information. Note, that the probabilities of the positive states of all nodes in the network are higher. This is because the evidence available (“John is sneezing”) supports the positive state of all the variables.
When John starts Sneezing the probabilities are updated to account for this information. Note, that the probabilities of the positive states of all nodes in the network are higher. This is because the evidence available (“John is sneezing”) supports the positive state of all the variables.
Fig. 9. Prerequisite relationship between two pieces of knowledge.
Fig. 9. Prerequisite relationship between two pieces of knowledge.
Fig. 10. A Bayesian network backbone for prerequisites.
Fig. 10. A Bayesian network backbone for prerequisites.
Fig. 11. A Bayesian student model based on misconceptions.
Fig. 11. A Bayesian student model based on misconceptions.
Fig. 12. A Bayesian network modeling granularity relationships.
Fig. 12. A Bayesian network modeling granularity relationships.
Fig. 13. A Bayesian network modeling granularity and prerequisite relationships simultaneously.
Fig. 13. A Bayesian network modeling granularity and prerequisite relationships simultaneously.
Fig. 14. A Bayesian network modeling granularity and prerequisite relationships simultaneously - with intermediate variable introduced One way of making the machine learning process more controlled is to introduce structural constraints (enforce or prohibit links between certain variables) and learn the reminder of the structure along with parameters or learn exclusively the parameters. The accuracy of the resulting model can be subsequently investigated.
Fig. 14. A Bayesian network modeling granularity and prerequisite relationships simultaneously - with intermediate variable introduced One way of making the machine learning process more controlled is to introduce structural constraints (enforce or prohibit links between certain variables) and learn the reminder of the structure along with parameters or learn exclusively the parameters. The accuracy of the resulting model can be subsequently investigated.
Fig. 15. A Bayesian network modeling two ways of a learner’s knowledge acquisition.
Fig. 15. A Bayesian network modeling two ways of a learner’s knowledge acquisition.
Fig. 16. A dynamic Bayesian network for student modeling. So far, we have discussed several simple BNs used to represent student’s features (mainly knowledge). The goal of this section is tc present a selection of more complex BNs that have been used to model a wide range of features and processes, such as: problem solving metacognitive skills, and emotional state and affect.
Fig. 16. A dynamic Bayesian network for student modeling. So far, we have discussed several simple BNs used to represent student’s features (mainly knowledge). The goal of this section is tc present a selection of more complex BNs that have been used to model a wide range of features and processes, such as: problem solving metacognitive skills, and emotional state and affect.
4.5.1. Problem solving A good example of modeling the problem solving process is the physics tutor ANDES (Conati et al.1997, 2002). The student model o} ANDES allows three kinds of assessment: a) plan recognition (discovering the most likely problem solving strategy that the student i: employing at a given point in time), b) prediction of student goals and actions, and c) long-time assessment of the student’s knowledge. A BN implemented in ANDES includes variables of the following types:
4.5.1. Problem solving A good example of modeling the problem solving process is the physics tutor ANDES (Conati et al.1997, 2002). The student model o} ANDES allows three kinds of assessment: a) plan recognition (discovering the most likely problem solving strategy that the student i: employing at a given point in time), b) prediction of student goals and actions, and c) long-time assessment of the student’s knowledge. A BN implemented in ANDES includes variables of the following types:
Fig. 18. A BN supporting the Explanation Based Learning of Correctness (EBLC).
Fig. 18. A BN supporting the Explanation Based Learning of Correctness (EBLC).
Fig. 19. A Bayesian network for the Prime Climb game. By the moment, the nodes defined account for the skills and precedence relationships to be taken into account when teaching the nplex algorithm. More nodes are needed to collect evidence about a student:
Fig. 19. A Bayesian network for the Prime Climb game. By the moment, the nodes defined account for the skills and precedence relationships to be taken into account when teaching the nplex algorithm. More nodes are needed to collect evidence about a student:
e Evidential problem nodes. As the simplex algorithm is a procedural domain, the evidential nodes are problems to be solved by the student. We therefore define propositional variables: Remember that the ability nodes have been defined as the set of skills necessary to solve certain kind of problems: in this way, there is a causal relationship between the ability and the problem. That is, only students who have the ability (i.e., the necessary set of skills) will be able to solve a particular problem.
e Evidential problem nodes. As the simplex algorithm is a procedural domain, the evidential nodes are problems to be solved by the student. We therefore define propositional variables: Remember that the ability nodes have been defined as the set of skills necessary to solve certain kind of problems: in this way, there is a causal relationship between the ability and the problem. That is, only students who have the ability (i.e., the necessary set of skills) will be able to solve a particular problem.
Fig. 20. A learning strategy for the simplex algorithm. Finally the Bayesian network that accounts for a student model for the Simplex algorithm is shown in Fig. 21. So now our BSM for the Simplex algorithm is finished. Recall that in this model there are only specific questions to test skills Sg to S14.
Fig. 20. A learning strategy for the simplex algorithm. Finally the Bayesian network that accounts for a student model for the Simplex algorithm is shown in Fig. 21. So now our BSM for the Simplex algorithm is finished. Recall that in this model there are only specific questions to test skills Sg to S14.
Fig. 21. A Bayesian student model for the Simplex algorithm.
Fig. 21. A Bayesian student model for the Simplex algorithm.

Related papers

Designing intelligent tutoring systems: a bayesian approach
Hugo Gamboa

Enterprise information systems III, 2002

This paper proposes a model and an architecture for designing intelligent tutoring system using Bayesian Networks. The design model of an intelligent tutoring system is directed towards the separation between the domain knowledge and the tutor shell. The architecture is composed by a user model, a knowledge base, an adaptation module, a pedagogical module and a presentation module. Bayesian Networks are used to assess user's state of knowledge and preferences, in order to suggest pedagogical options and recommend future steps in the tutor. The proposed architecture is implemented in the Internet, enabling its use as an e-learning tool. An example of an intelligent tutoring system is shown for illustration purposes.

View PDFchevron_right
A Bayesian Network Model for More Natural Intelligent Tutoring Systems
Intisar Hussien

A key element in the design of Intelligent Tutoring Systems (ITS) is to fit the learning plan to the individual variances of learners. We studied this problem by modeling a dependency relationship between concepts of a Java programing course within a Bayesian network. Our model was established on the basis of experts' views, corroborated by experimental investigation. We found that the tested programing concepts do, indeed, exhibit dependency relationships, which could minimize the learning time of the individuals, if they were taken into account. This, implies that for the design of a more natural ITS, it is helpful to consider the existent concept dependency, so as toenhance the role of individual differences between the learners and, hence, minimize the learning time.

View PDFchevron_right
Evaluation module based on Bayesian networks to Intelligent Tutoring Systems
Alan david Ramirez Noriega

International Journal of Information Management, 2017

Assessing knowledge acquisition by the student is the primary task of an Intelligent Tutoring System (ITS). Assessment is needed to adapt learning materials and activities to student's capacities. In this paper, a proposal to infer the level of knowledge possessed by the student is presented. A general structure of an ITS is shown, an evaluation module based on Bayesian network is proposed. The module mainly based on a test was implemented to know what student knows. During the test, the software system chooses the new questions based on the responses to the previous ones, that is, the software system makes an adaption in real time. A network of concepts was used to get the inferences, which contains the relationships between concepts. Evaluation module could infer many questions and concepts through the relations and the probabilistic inference of the Bayesian network. It information easily can be used to reinforce weak topics in order to cover the student's needs. Given the positive evidence is considered that testing the rest of variable examined in the Bayesian network can provide better accurate in the diagnostic of student' knowledge possession.

View PDFchevron_right
Adaptive Bayesian networks for multilevel student modelling
Eva Millán

Intelligent Tutoring Systems, 2000

In this paper we present an integrated theoretical approach for student modelling based on an Adaptive Bayesian Network. A mathematical formalization of the Adaptive Bayesian Network is provided, and new question selection criteria presented. Using this theoretical framework, a tool to assist in the diagnosis process has been implemented. This tool allows the definition of Bayesian Adaptive Tests in an easy way: the only specifications required are a curriculum-based structured domain (together with a set of weights) and a set of questions about the domain (the item pool), which will be internally converted into a Bayesian Network. In this way, we intend to make available this theoretically sound technology to educators, minimizing the knowledge engineering effort required.

View PDFchevron_right
Toward an Adaptive Learning System Framework: Using Bayesian Network to Manage Learner Model
K59 Nguyen Phuong Anh

International Journal of Emerging Technologies in Learning (iJET), 2012

This paper represents a new approach to manage learner modeling in an adaptive learning system framework. It considers developing the basic components of an adaptive learning system such as the learner model, the course content model and the adaptation engine. We use the overlay model and Bayesian network to evaluate learnersâ?? knowledge. In addition, we also propose a new content modeling method as well as adaptation engine to generate adaptive course based on learnerâ??s knowledge. Based on this approach, we developed an adaptive learning system named is ACGS-II, that teaches students how to design an Entity Relationship model in a database system course. Empirical testing results for students who used the application indicate that our proposed model is very helpful as guidelines to develop adaptive learning system to meet learnersâ?? demands.

View PDFchevron_right
<i>Bayesian student modeling and the problem of parameter specification</i>
John-Mark Agosta

British Journal of Educational Technology, 2001

In this paper, the application of Bayesian networks to student modeling is discussed. A review of related work is made, and then the structural model is defined. Two of the most commonly cited reasons for not using Bayesian networks in student modeling are the computational complexity of the algorithms and the difficulty of the knowledge acquisition process. We propose an approach to simplify knowledge acquisition. Our approach applies causal independence to factor the conditional probabilities and decrease the parameters required for each question to a number linear in the number of concepts. This also provides the new parameters with an intuitive meaning that makes their specification easier. Finally, we present an example to illustrate the use of our approach.

View PDFchevron_right
Developing a Pedagogical Intervention Support based on Bayesian Networks
Andrey Chukhray

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.

View PDFchevron_right
A Bayes Net Toolkit for Student Modeling in Intelligent Tutoring Systems
Kai-min Chang, Jack Mostow

Lecture Notes in Computer Science, 2006

This paper describes an effort to model a student's changing knowledge state during skill acquisition. Dynamic Bayes Nets (DBNs) provide a powerful way to represent and reason about uncertainty in time series data, and are therefore well-suited to model student knowledge. Many general-purpose Bayes net packages have been implemented and distributed; however, constructing DBNs often involves complicated coding effort. To address this problem, we introduce a tool called BNT-SM. BNT-SM inputs a data set and a compact XML specification of a Bayes net model hypothesized by a researcher to describe causal relationships among student knowledge and observed behavior. BNT-SM generates and executes the code to train and test the model using the Bayes Net Toolbox [1]. Compared to the BNT code it outputs, BNT-SM reduces the number of lines of code required to use a DBN by a factor of 5. In addition to supporting more flexible models, we illustrate how to use BNT-SM to simulate Knowledge Tracing (KT) , an established technique for student modeling. The trained DBN does a better job of modeling and predicting student performance than the original KT code (Area Under Curve = 0.610 > 0.568), due to differences in how it estimates parameters.

View PDFchevron_right
Adaptive user support in educational environments: A Bayesian Network approach
Christos Fidas, Nikolaos Tselios

SUMMARY This paper is concerned with the design and implementation of an innovative user support system in the frame of an open educational environment. The environment adapted is ModelsCreator (MC), an educational system supporting learning through modelling activities. The pupils' typical interaction with the system was modelled using Bayesian Belief Networks (BBN). This model has been used in ModelsCreator to build an adaptive help system providing the most useful guidelines according to the current state of interaction. A brief description of the system and an overview of application of Bayesian techniques to educational systems is presented together with discussion about the process of building of the Bayesian Network derived from actual student interaction data. A preliminary evaluation of the developed prototype indicates that the proposed approach produces systems with promising performance.

View PDFchevron_right
A Student Modeling Based on Bayesian Network Framework for Characterizing Student Learning Style
Indriana Hidayah

Advanced Science Letters, 2014

Students have different characteristics of learning, depending on knowledge, interest, learning style, and background. General learning materials for each student may not be properly accepted and will yield ineffective learning process. Therefore, implementation of suitable learning model in term of student characteristic is needed. Specifically, in conventional (face-toface) learning method where the number of student was large, knowing the character of each student is important yet difficult. Conventional learning is the main learning method applied in undergraduate program of Electrical Engineering and Information Technology, Universitas Gadjah Mada (UGM). Thus, finding an appropriate technique to understand student characteristic is important. In this paper, a student modeling based on Bayesian network method is constructed and presented in a conventional learning environment. Bayesian network method is a modeling tool based on causality in the set of random variables that can be used in variety of applications, for instance in the context of education. Bayesian network was implemented by applying K2 algorithm to determine the learning style of each student in English course held in undergraduate program of Electrical Engineering and Information Technology UGM as a case. The evaluation results showed that accuracy of the model reach a value of 80%. It indicated that the model was closely representing the real dataset.

View PDFchevron_right

References (63)

  1. Anderson, J., Corbett, A., Koedinger, K., & Pelletier, R. (1995). Cognitive tutors: lessons learned. The Journal of the Learning Sciences, 4(2), 167-207.
  2. Arroyo, I., & Woolf, B. P. (2005). Inferring learning and attitudes from a Bayesian network of log file data. Frontiers in Artificial Intelligence and Applications, 125.
  3. Baker, R., Corbett, A. T., & Aleven, V. (2008). More accurate student modeling through contextual estimation of slip and guess probabilities in Bayesian knowledge tracing. Lecture Notes in Computer Science, 5091, 406-415.
  4. Beck, J.E., 2007. Difficulties in inferring student knowledge from observations (and why you should care). In: Proceedings of AIED2007 Workshop on Educational Data Mining (EDM'07). pp. 21-30.
  5. Brown, J. S., & Burton, R. R. (December 1978). Diagnostic models for procedural bugs in basic mathematics skills. Cognitive Science, 2, 155-192.
  6. Brusilovsky, P., & Millán, E. (2007). User models for adaptive hypermedia and? adaptive? educational systems. In P. Brusilovsky, A. Kobsa, & W. Nejdl (Eds.), The Adaptive Web. vol. 4321 of lecture notes in computer science (pp. 3-53). Berlin, Heidelberg: Springer.
  7. Burton, R. R., & Brown, J. S. (1982). An investigation of computer coaching for informal learning activities. In D. Sleeman, & J. S. Brown (Eds.), Proceedings of international conference on Intelligent Tutoring Systems (ITS'82) (pp. 79-98).
  8. Carbonell, J. R. (1970). AI in CAI: an artificial intelligence approach to computer-assisted instruction. IEEE Transactions on Man-Machine Systems, 11(4), 190-202.
  9. Charniak, E. (1991). Bayesian networks without tears. AI Magazine, 12(4), 50-63.
  10. Cipra, B. (May 2000). The best of the 20th century: editors name top 10 algorithms. SIAM News, 33(4).
  11. Collins, J., Greer, J., Huang, S. (1996). Adaptive assessment using granularity hierarchies and bayesian nets. In: Lecture Notes in Computer Science. Vol. 1086. pp. 569-577.
  12. Conati, C., Gertner, A., & VanLehn, K. (November 2002). Using bayesian networks to manage uncertainty in student modeling. User Modeling and User-Adapted Interaction, 12(4), 371-417.
  13. Conati, C., Gertner, A. S., VanLehn, Druzdzel, M. (1997). On-line student modeling for coached problem solving using bayesian networks. In: Proceedings of UM'97, Sixth International Conference on User Modeling. pp. 231-242.
  14. Conati, C., & Maclaren, H. (January 2009). Empirically building and evaluating a probabilistic model of user affect. User Modeling and User-Adapted Interaction, 19(3), 267-303.
  15. Cooper, G. F. (March 1990). The computational complexity of probabilistic inference using bayesian belief networks. Artificial Intelligence, 42(2-3), 393-405. Fig. 21. A Bayesian student model for the Simplex algorithm.
  16. Corbett, A., & Anderson, J. (1992). Student modeling and mastery learning in a computer-based programming tutor. Lecture Notes in Computer Science, Vol. 608, 413-420.
  17. Corbett, A. T., Anderson, J. R., & O'Brien, A. T. (1995). Student modeling in the act programming tutor. In S. F. Nichols, R. L. Chipman, & R. L. Brennan (Eds.), Cognitively diagnostic assessment (pp. 19-41). Erlbaum.
  18. Dean, T., & Kanazawa, K. (1989). A model for reasoning about persistence and causation. Tech. rep. Providence, RI, USA: Brown University.
  19. Díez, F.-J., & Druzdel, M. (2002). Canonical probabilistic models for knowledge engineering. Tech. Rep. IA-02-01. Dept. Inteligencia Artificial.
  20. Druzdzel, M., Henrion, M. (1990). Using scenarios to explain probabilistic inference. In: Working notes of the AAAI Workshop on Explanation. pp. 133-141.
  21. Druzdzel, M. J., & van Leijen, H. (2001). Causal reversibility in Bayesian networks. Journal of Experimental and Theoretical Artificial Intelligence, 13(1), 45-62.
  22. Duda, R. O., & Hart, P. E. (1973). Pattern classification and scene analysis. New York: Wiley-Interscience Publication.
  23. Greer, J., & McCalla, G. (1989). A computational framework for granularity and its application to educational diagnosis. In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI'89) (pp. 477-482). San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.
  24. Greer, J. E., & McCalla, G. I. (Eds.). (1994). Student modelling: The key to individualized knowledge-based instruction. Vol. 125 of Nato ASI Series F: Computer and systems sciences. Springer Verlag.
  25. Jameson, A. (1996). Numerical uncertainty management in user and student modeling: an overview of systems and issues. User Modeling and User-Adapted Interaction, 5(3-4), 193-251.
  26. Kahneman, D., Slovic, P., & Tversky, A. (1982). Judgment under uncertainty: Heuristics and biases. New York: Cambridge University Press.
  27. Kasurinen, J., & Nikula, U. (2009). Estimating programming knowledge with Bayesian knowledge tracing. Computer Science Education 313-317.
  28. Lauritzen, S. L., & Spiegelhalter, D. J. (1988). Local computations with probabilities on graphical structures and their application to expert systems. Journal of the Royal Statistical Society B, 50, 157-224.
  29. Liu, C.-l. (2008). Using bayesian networks for student modeling. In R. M. Viccari, P. Augustin-Jaques, & R. Verdin (Eds.), Agent-based tutoring systems by cognitive and affective modeling (pp. 97-113). Igi Global.
  30. López, J.-M., Millán, E., Pérez de la Cruz, J.-L., Triguero, F. (1998). Ilesa: a web-based intelligent learning environment for the simplex algorithm. In: Proceedings of Inter- national Conference on Computer-Aided Learning and Instruction (CALISCE'98). pp. 399-406.
  31. Manske, M., Conati, C. (2005). Modelling learning in an educational game. In: Proceedings of AIED'05: World Conference of Artificial Intelligence and Education. pp. 411-419.
  32. Mayo, M., & Mitrovic, A. (2001). Optimising its behavior with bayesian networks and decision theory. International Journal of Artificial Intelligence in Education, 12, 124-153.
  33. Millán, E., García-Hervás, E., Guzmán De los Riscos, E., Rueda, A., & Pérez de la Cruz, J.-L. (2004). Tapli: an adaptive web-based learning environment for linear programming. In Current topics in artificial intelligence. Vol. 3040 of lecture notes in artificial intelligence (pp. 676-685). Springer.
  34. Millán, E., & Pérez-de-la Cruz, J.-L. (June 2002). A bayesian diagnostic algorithm for student modeling and its evaluation. User Modeling and User-Adapted Interaction, 12(2), 281-330.
  35. Millán, E., Pérez-de-la Cruz, J.-L., & García, F. (2003). Dynamic versus static student models based on bayesian networks: an empirical study. In Proceedings of Knowledge-based Intelligent Information and Engineering Systems (KES'03). Vol. 2774 of lecture notes in computer science (pp. 1337-1344). Springer.
  36. Mitrovic, A. (2003). An intelligent sql tutor on the web. International Journal of Artificial Intelligence in Education, 13(2-4), 173-197.
  37. Mitrovic, A., Koedinger, K. R., & Martin, B. (2003). A Comparative analysis of cognitive tutoring and constraint-based modeling, Vol. 2702. Berlin, Heidelberg: Springer Berlin Heidelberg.
  38. Muldner, K., Christopherson, R., Atkinson, R., & Burleson, W. (2009). Investigating the utility of eye-tracking information on affect and reasoning for user modeling, Vol. 5535. Berlin, Heidelberg: Springer Berlin Heidelberg.
  39. Muldner, K., & Conati, C. (2005). Using similarity to infer meta-cognitive behaviors during analogical problem solving. In: Proceedings of International Conference on User Modeling (UM'05). In Lecture Notes in Computer Science, Vol. 3538 (pp. 134-143).
  40. Neapolitan, R. (1990). Probabilistic reasoning in expert systems: Theory and algorithms. New York: John Wiley & Sons.
  41. Ohlsson, S. (1992). Constraint-based student modeling. Journal of Artificial Intelligence in Education, 3(4), 429-447.
  42. Ortony, A., Clore, G. L., & Collins, A. (July 1988). The cognitive structure of emotions. Cambridge University Press.
  43. Pardos, Z. A., & Heffernan, N. T. (2010). Modeling individualization in a Bayesian networks implementation of knowledge tracing. In Proceedings of User Modeling, Adaptation, and Personalization, (UMAP'2010): Vol. 6075 of lecture notes in computer science (pp. 255-266). Springer.
  44. Pearl, J. (1985). Bayesian networks: A model of self-activated memory for evidential reasoning. (UCLA Technical Report CSD-850017).
  45. Pearl, J. (1986). Fusion, propagation, and structuring in belief networks. Artificial Intelligence, 29, 241-288.
  46. Pearl, J. (1988). Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann Publishers. Pearl, J. (June 2000). Causality: Models, reasoning and inference (2nd ed.). Cambridge University Press.
  47. Pourret, O., Naïm, P., & Marcot, B. (2008). Bayesian networks: A practical guide to applications. Wiley Interscience.
  48. Reye, J. (1996). A belief net backbone for student modelling. In Proceedings of International Conference on Intelligent Tutoring Systems (ITS'96). Vol. 1086 of lecture notes in computer science (pp. 596-604). Springer.
  49. Reye, J. (1998). Two-phase updating of student models based on dynamic belief networks. In Proceedings of International Conference on Intelligent Tutoring Systems (ITS'98). Vol. 1452 of lecture notes in computer science (pp. 274-283). Springer.
  50. Reye, J. (2004). Student modeling based on belief networks. International Journal of Artificial Intelligence in Education, 14, 1-33.
  51. Russell, S., & Norvig, P. (December 2002). Artificial intelligence: A modern approach (2nd ed.). Prentice Hall.
  52. Self, J. (1988). Bypassing the intractable problem of student modelling. In: Proceedings of International Conference on Intelligent Tutoring Systems (ITS'98). pp. 107-123.
  53. Self, J. (1994). Formal approaches to student modeling. In J. E. Greer, & G. I. McCalla (Eds.), Student modelling: The key to individualized knowledge-based instruction. Vol. 125 of. Nato ASI Series F: Computer and systems sciences (pp. 295-352). Springer Verlag.
  54. Self, J. (1999). The defining characteristics of intelligent tutoring system research: ITSs care, precisely. International Journal of Artificial Intelligence in Education, 10, 350-364.
  55. Stacey, K., Sonenberg, L., Nicholson, A., Boneh, T., & Steinle, V. (2003). A teaching model exploiting cognitive conflict driven by a bayesian network. InLecture notes in computer science, Vol. 2702 (pp. 145).
  56. Suebnukarn, S., & Haddawy, P. (September 2006). Modeling individual and collaborative problem-solving in medical problem-based learning. User Modeling and User-Adapted Interaction, 16(3-4), 211-248.
  57. Ting, C.-Y. T., & Phon-Amnuaisuk, S. (2009). Log data approach to acquisition of optimal bayesian learner model. American Journal of Applied Sciences, 6(5), 913-921.
  58. VanLehn, K., Niu, Z., Siler, S., & Gertner, A. S. (1998). Student modeling from conventional test data: a Bayesian approach without priors. InLecture notes in computer science, Vol. 1452 (pp. 434-443). Berlin, Heidelberg: Springer Berlin Heidelberg.
  59. Weisberg, M. (2007). Who is a modeler? British Journal for Philosophy of Science, 58, 207-233.
  60. Wenger, E. (1987). Artificial intelligence and tutoring systems: Computational approaches to the communication of knowledge. Los Altos, CA: Morgan Kaufman.
  61. Yudelson, M. V., Medvedeva, O. P., & Crowley, R. S. (2008). A multifactor approach to student model evaluation. User Modeling and User-Adapted Interaction, 18(4), 349-382.
  62. Zapata-Rivera, J. D. (October 2004). Inspectable bayesian student modelling servers in multi-agent tutoring systems. International Journal of Human-Computer Studies, 61(4), 535-563.
  63. Zukerman, I., & Albrecht, D. W. (March 2001). Predictive statistical models for user modeling. User Modeling and User-Adapted Interaction, 11(1), 5-18.

Related papers

Using Bayesian Networks to Manage Uncertainty in Student Modeling
Update Pola

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.

View PDFchevron_right
On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks
Nobita Ska

1997

This paper describes the student modeling component of ANDES, an Intelligent Tutoring System for Newtonian physics. ANDES' student model uses a Bayesian network to do long-term knowledge assessment, plan recognition and prediction of students' actions during problem solving. The network is updated in real time, using an approximate anytime algorithm based on stochastic sampling, as a student solves problems with ANDES. The information in the student model is used by ANDES' Help system to tailor its support when the student reaches impasses in the problem solving process. In this paper, we describe the knowledge structures represented in the student model and discuss the implementation of the Bayesian network assessor. We also present a preliminary evaluation of the time performance of stochastic sampling algorithms to update the network. ?

View PDFchevron_right
Bayesian Student Modeling in the AC Tutor
slavomir stankov

Adaptive Instructional Systems, 2020

The reasoning process about the level of student's knowledge can be challenging even for experienced human tutors. The Bayesian networks are a formalism for reasoning under uncertainty, which has been successfully used for various artificial intelligence applications, including student modeling. While Bayesian networks are a highly flexible graphical and probabilistic modeling framework, its main challenges are related to the structural design and the definition of "a priori" and conditional probabilities. Since the AC&NL Tutor's authoring tool automatically generates tutoring elements of different linguistic complexity, the generated sentences and questions fall into three difficulty levels. Based on these levels, the probability-based Bayesian student model is proposed for mastery-based learning in intelligent tutoring system. The Bayesian network structure is defined by generated questions related to the node representing knowledge in a sentence. Also, there are relations between inverse questions at the same difficulty level. After the structure is defined, the process of assigning "a priori" and conditional probabilities is automated using several heuristic expert-based rules.

View PDFchevron_right
Designing a Dynamic Bayesian Network for Modeling Students? Learning Styles
Eva Millán

Eighth IEEE International Conference on …, 2008

When using Learning Object Repositories, it is interesting to have mechanisms to select the more adequate objects for each student. For this kind of adaptation, it is important to have sound models to estimate the relevant features. In this paper we present a student model to account for Learning Styles, based on the model defined by Felder and Sylverman and implemented using Dynamic Bayesian Networks. The model is initialized according to the results obtained by the student in the Index of Learning Styles Questionnaire, and then fine-tuned during the course of the interaction using the bayesian model, The model is then used to classify objects in the repository as appropriate or not for a particular student.

View PDFchevron_right
Bayesian Student Modeling in the AC&NL Tutor
Angelina Gaspar

2020

The reasoning process about the level of student’s knowledge can be challenging even for experienced human tutors. The Bayesian networks are a formalism for reasoning under uncertainty, which has been successfully used for various artificial intelligence applications, including student modeling. While Bayesian networks are a highly flexible graphical and probabilistic modeling framework, its main challenges are related to the structural design and the definition of “a priori” and conditional probabilities. Since the AC&NL Tutor’s authoring tool automatically generates tutoring elements of different linguistic complexity, the generated sentences and questions fall into three difficulty levels. Based on these levels, the probability-based Bayesian student model is proposed for mastery-based learning in intelligent tutoring system. The Bayesian network structure is defined by generated questions related to the node representing knowledge in a sentence. Also, there are relations between...

View PDFchevron_right

Related topics

  • User Modeling
  • Bayesian Networks
  • Computers in Education
  • Tutoring System
  • Bayesian Network
  • Graphical Model

    • Cited by

    A dynamic bayesian network for inference of learners' algebraic knowledge
    Henrique Seffrin

    Proceedings of the 29th Annual ACM Symposium on Applied Computing - SAC '14, 2014

    An Intelligent Tutoring System (ITS) is an educational software that provides personal assistance for students, allowing them to learn at their own pace. This is possible because ITSs are able to map the learners' knowledge to create a student model. Most of the tutors use a Bayesian Network (BN) to perform this task, due to their ability to deal with uncertain data. However, classic static BNs are unable to model data, such as the student's knowledge, that changes over time. Dynamic Bayesian Networks (DBN) are an interesting option in this case, because they are a special type of BN that reasons over time. This paper presents an architecture of DBN that aims at inferring student's algebraic knowledge. This network was constructed based on a concept map, which was developed with the goal of structuring the algebraic knowledge, i. e. defining relationships among concepts. The proposed DBN was evaluated with the help of an expert in order to verify the ability of the network to predict the student's knowledge on the application of operations to solve 1 st degree equations. This DBN is being integrated into an web-based ITS for algebra learning.

    View PDFchevron_right
    Converting Graphic Relationships into Conditional Probabilities in Bayesian Network
    academic network

    Bayesian Inference

    Bayesian network (BN) is a powerful mathematical tool for prediction and diagnosis applications. A large Bayesian network can constitute many simple networks, which in turn are constructed from simple graphs. A simple graph consists of one child node and many parent nodes. The strength of each relationship between a child node and a parent node is quantified by a weight and all relationships share the same semantics such as prerequisite, diagnostic, and aggregation. The research focuses on converting graphic relationships into conditional probabilities in order to construct a simple Bayesian network from a graph. Diagnostic relationship is the main research object, in which sufficient diagnostic proposition is proposed for validating diagnostic relationship. Relationship conversion is adhered to logic gates such as AND, OR, and XOR, which are essential features of the research.

    View PDFchevron_right
    Bayesian Student Modeling in the AC&NL Tutor
    Angelina Gaspar

    2020

    The reasoning process about the level of student’s knowledge can be challenging even for experienced human tutors. The Bayesian networks are a formalism for reasoning under uncertainty, which has been successfully used for various artificial intelligence applications, including student modeling. While Bayesian networks are a highly flexible graphical and probabilistic modeling framework, its main challenges are related to the structural design and the definition of “a priori” and conditional probabilities. Since the AC&NL Tutor’s authoring tool automatically generates tutoring elements of different linguistic complexity, the generated sentences and questions fall into three difficulty levels. Based on these levels, the probability-based Bayesian student model is proposed for mastery-based learning in intelligent tutoring system. The Bayesian network structure is defined by generated questions related to the node representing knowledge in a sentence. Also, there are relations between...

    View PDFchevron_right
    Expectations of Students from Classroom Rules: A Scenario Based Bayesian Network Analysis
    Ahmet Başal

    Participatory educational research, 2023

    Classroom rules are a fundamental aspect of classroom management and ensuring compliance with established rules is crucial. Previous research has shown that students often pay little attention to the development of classroom rules. This quantitative study aims to investigate the expectations that students have concerning classroom rules. To this end, a 4-point Likert scale questionnaire consisting of 30 items was administered to 356 secondary school students. The Bayesian Search method and expert opinion were used to obtain a Bayesian Network model. The findings of the study indicate that students expect rules to be determined at the beginning of the academic year, wish to be involved in the determination process, and prefer minimal changes to the rules. They also expect a limited number of rules and reinforcement from teachers for displaying desirable behavior. Additionally, the study found that students are more likely to adhere to classroom rules in a clean and uncrowded environment, and prefer that their parents are not informed about these rules. The results also suggest that increased adherence to classroom rules leads to increased class inclusion, while decreased adherence results in decreased class inclusion. Furthermore, the study found that adoption of classroom rules leads to increased in-class cohesion, while non-adoption results in decreased cohesion. These findings contribute to the existing body of knowledge concerning student expectations of classroom rules.

    View PDFchevron_right
    Evaluating Two Approaches to Assessing Student Progress in Cybersecurity Exercises
    Valdemar Švábenský

    Proceedings of the 53rd ACM Technical Symposium on Computer Science Education

    Cybersecurity students need to develop practical skills such as using command-line tools. Hands-on exercises are the most direct way to assess these skills, but assessing students' mastery is a challenging task for instructors. We aim to alleviate this issue by modeling and visualizing student progress automatically throughout the exercise. The progress is summarized by graph models based on the shell commands students typed to achieve discrete tasks within the exercise. We implemented two types of models and compared them using data from 46 students at two universities. To evaluate our models, we surveyed 22 experienced computing instructors and qualitatively analyzed their responses. The majority of instructors interpreted the graph models effectively and identified strengths, weaknesses, and assessment use cases for each model. Based on the evaluation, we provide recommendations to instructors and explain how our graph models innovate teaching and promote further research. The impact of this paper is threefold. First, it demonstrates how multiple institutions can collaborate to share approaches to modeling student progress in hands-on exercises. Second, our modeling techniques generalize to data from different environments to support student assessment, even outside the cybersecurity domain. Third, we share the acquired data and open-source software so that others can use the models in their classes or research.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved