Developing Computer-Aided Diagramming Tools to Mine, Model, and Support Students' Reasoning Processes

• In Event: Validity of Insights Derived From Learning Technology Log Data

Abstract

Despite 40 years of research, very little research reveal the cognitive processes that explain how computer-aided diagramming tools affect learning. Using a diagramming tool developed to mine students’ actions while diagramming complex arguments, the mined data was used to develop algorithms to operationalize and measure students’ use of backward, forward, breadth, depth-first reasoning that best predict students’ diagram scores. The findings show that observing the placement of just the first five nodes moved on screen provides sufficient data to generate backward/forward and breadth/depth-first ratio scores to predict diagram scores and that greater use of backward and depth-first processing produces better diagrams – particularly on depth of analysis. This study presents new methods for integrating learning analytics into computer-aided diagramming tools.

Author

• Allan C. Jeong, Florida State University