Exploring Representational Flexibility Development Through Speech Data Mining

• In Event: Technology, Instruction, Cognition and Learning SIG. Assessment With Technology: Diverse Data, Collection, and Use

Abstract

Representational flexibility is a critical index for the practices of problem solving in the STEM domains. The current study aims to explore the development and assessment of representational flexibility via real-time data mining with the speech data from learners who were involved in simulation-based design and scientific problem solving. We implemented two speech data mining approaches: (1) developing a competency-classification model and (2) using the similarity index. The findings indicated that the two approaches of speech or text data mining can act as the in-situ performance assessment methods to evaluate the representational flexibility development of a heterogeneous learner group. The study also suggested that virtual-reality supported simulation and game design can act as primers for representational flexibility acquisition and assessment.

Authors

• Fengfeng Ke, Florida State University

• Jewoong Moon, Florida State University