Evaluating Teaching Competency in a 3D E-Learning Environment Using a Small-Scale Bayesian Network
Year: 2016
Type: article
Abstract: This exploratory study examined the usage of a Bayesian network to evaluate the teaching performance of university teaching assistants in an e-learning (or e-training) session. The researchers built a 3D virtual realitybased classroom for teaching training, and collected performance data from 23 volunteer international teaching assistants. The researchers assessed the teaching performance of lecturing, interaction with students, and classroom management, and developed a data-driven competency model. We coded the recorded teaching performance data every 30 seconds, and used the coded frequency of each teaching facet performance to calibrate the conditional probability tables for the Bayesian network development. The outcome network would potentially help the development of an intelligent agent that evaluates a teaching assistant’s real-time teaching performance and adaptively provides varied scaffolds or prompts. We examined this specific case as an example of mining the data generated in a 3D virtual reality-based e-learning environment for both instructors and learners.
Authors: Xinhao Xu, Fengfeng Ke, Sungwoong Lee
Institutions: Florida State University, Emporia State University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: bronze
OpenAlex ID: W2961465060