Developing Bayes Nets for Modeling Student Cognition in Digital and Nondigital Assessment Environments

• In Event: Poster Session 10
  In Poster Session: Assessment of Learning and Cognition

Abstract

Development of digital activities in assessments has led to collection and storage of information about individual activities on a large scale. Data from student interactions in digital learning environments can be captured “invisibly” as learning is occurring. The study demonstrates evidence identification and aggregation of learning progression data from diverse assessment environments including two digital activities, traditional assessment, and teacher ratings based on observation of in-person non-digital activity. Bayesian network models are developed and fitted to a sample dataset to facilitate reasoning about student learning progression. Results of the study can be used to support inferences about students’ levels of learning proficiency as well as to provide information about their cognition as they progress learning activities.

Authors

• Yuning Xu, Arizona State University

• Roy Levy, Arizona State University

• Kristen E. Dicerbo, Pearson

• Emily R. Lai, Pearson

• Laura Holland, Pearson Education, Inc.