• Publications
  • Influence
Modeling Diagnostic Assessments with Bayesian Networks
This paper defines Bayesian network models and examines their applications to IRT-based cognitive diagnostic modeling. Expand
A Tough Nut to Crack: Measuring Collaborative Problem Solving
The purpose of our project is to explore the measurement of cognitive skills in the domain of science through collaborative problem solving tasks, measure the collaborative skills, and gauge theExpand
Interacting with Inspectable Bayesian Student Models
This paper presents ViSMod (Visualization of Bayesian Student Models) an integrated tool to visualize and inspect distributed Bayesian student models. Expand
Evidence-based Approach to Interacting with Open Student Models
This paper (a) presents an evidence-based approach to interacting with open student models, evidentiary arguments and evidence-centered design, (b) illustrates this approach in the context of an assessment-based learning environment called Math Intervention Module (MIM). Expand
Inspecting and Visualizing Distributed Bayesian Student Models
We present a multipleview application, ViSMod, that has been designed and built to allow students and teachers to experiment with creation of Bayesian what-if scenarios; providing not only a visualization tool, but also an interactive tool for inspection of and reflection on Bayesian student models. Expand
Keeping your audience in mind: applying audience analysis to the design of interactive score reports
Score reports have one or more intended audiences: the people who use the reports to make decisions about test takers, including teachers, administrators, parents and test takers. Attention toExpand
Assessing Science Inquiry Skills Using Trialogues
Trialogue-based tasks can be used to gather evidence that may be difficult to obtain using traditional assessment approaches, such as embedded questions. Expand
Construction and inspection of learner models
Learners working on the creation of conceptual maps become involved in a creative learning activity that involves "making sense" of new concepts and their relationships through modelling. Expand
Externalising Learner Modelling Representations
We develop ViSMod, an interactive visualization tool for Bayesian learner models and ConceptLab, a knowledge construction and navigation system that uses XML-based conceptual maps to represent the learner's view of the domain. Expand
Visualization of Bayesian Belief Networks
This paper describes the visualization techniques in VisNet and reports the main results found in the usability study. Expand