On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks

Conati, Cristina; Gertner, Abigail S.; VanLehn, Kurt; Drużdżel, Marek J.

doi:10.1007/978-3-7091-2670-7_24

Cited by 156 publications

(104 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Jebara [16], uses CHMMS, which are a particular case of Dynamic Bayesian Networks, to perform, first analysis, and then synthesis, of a player's behavior in a game. Conati et al [10] have built an intelligent tutoring system able to perform knowledge assessment, plan recognition and prediction of students' actions during problem solving using Bayesian networks. Jameson [15], provides a useful overview of student modeling techniques, and compares the Bayesian network approach with other popular modeling techniques.…”

Section: Bayesian Network For User Modeling and Interactive Narrativementioning

confidence: 99%

Natural interaction in intelligent spaces: Designing for architecture and entertainment

Sparacino¹

2008

Multimed Tools Appl

View full text Add to dashboard Cite

The rapid evolution of computers' processing power, progress in projection and display technology, and their low cost, accompanied by recent advances in mathematical modeling, make available to space designers today sophisticated technologies which were once accessible only to research institutions or large companies. Thanks to wireless sensing techniques it is possible to endow a space with perceptual intelligence, and make it aware of how people use it, move in it, or react to it. Intelligent Spaces are relevant for several applications or tasks which range from surveillance to entertainment, from medical rehabilitation to artistic performance, from museum exhibit design to commerce. The author's work focuses on Narrative Spaces which are storytellers, able to articulate an informative or entertaining audio-visual narration for people interactively. Narrative Spaces communicate by use of large scale coordinated projections, sounds and displays whose contents are choreographed by the natural body movements or physical gestures of the people in them. This paper describes the guiding principles and modeling approaches that, according to the author, enable a robust modeling of user input and communication strategies for digital content presentation in Intelligent Narrative Spaces. It then provides examples of applications built according to the specified criteria.

show abstract

Section: Bayesian Network For User Modeling and Interactive Narrativementioning

confidence: 99%

Natural interaction in intelligent spaces: Designing for architecture and entertainment

Sparacino¹

2008

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Different graphical models, such as Bayesian networks, dependency networks, inference networks, and causal models, have been used to model computer software users (Horvitz et al, 1998), car drivers (Pynadath & Wellman, 1995), students (Conati et al, 1997) and other social phenomena (McKim & Turner, 1997). Choosing the graphical modelling approach as a unified framework to combine multiple forms of evidence is motivated by the prior research.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Third, it can easily combine prior knowledge (such as partial information about the causal relationship) with data. This approach has been applied to model computer software users (Horvitz et al, 1998), car drivers (Pynadath & Wellman, 1995), and students (Conati et al, 1997).…”

Section: Graphical Models For Adaptive Complex User Modelingmentioning

confidence: 99%

Complex adaptive filtering user profile using graphical models

Zhang

2008

Information Processing & Management

View full text Add to dashboard Cite

This article explores how to develop complex data driven user models that go beyond the bag of words model and topical relevance. We propose to learn from rich user specific information and to satisfy complex user criteria under the graphical modelling framework. We carried out a user study with a web based personal news filtering system, and collected extensive user information, including explicit user feedback, implicit user feedback and some contextual information. Experimental results on the data set collected demonstrate that the graphical modelling approach helps us to better understand the complex domain. The results also show that the complex data driven user modelling approach can improve the adaptive information filtering performance. We also discuss some practical issues while learning complex user models, including how to handle data noise and the missing data problem.

show abstract

“…To this end, we have used a Bayesian student model (BSM) based on Bayesian Networks (BNs). The BN paradigm was chosen because it has proven to be a sound methodology for the student modeling problem, and it has been used with this purpose in a number of existing applications (Collins et al, 1996;Conati et al, 1997;VanLehn et al, 1998;Jameson, 1996). This previous research has shown that a BSM allows for a sound and detailed evaluation of each student, according to the granularity level defined by teachers.…”

Section: Introductionmentioning

confidence: 99%

Using Bayesian networks to improve knowledge assessment

Millán

Descalço

Castillo

et al. 2013

Computers & Education

View full text Add to dashboard Cite

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.

show abstract

On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks

Cited by 156 publications

References 9 publications

Natural interaction in intelligent spaces: Designing for architecture and entertainment

Natural interaction in intelligent spaces: Designing for architecture and entertainment

Complex adaptive filtering user profile using graphical models

Using Bayesian networks to improve knowledge assessment

Contact Info

Product

Resources

About