PhD Proposal by Sungeun An

Primary tabs

Title: A Computational Model of Self-Directed Learning for Systems Thinking


Sungeun An

Ph.D. Candidate in Human-Centered Computing

School of Interactive Computing

Georgia Institute of Technology


Date: Wednesday, December 1, 2021

Time: 2:00 PM - 4:00 PM EST

Location(Remote via BlueJeans): https://gatech.bluejeans.com/3291125456



Dr. Ashok Goel (Advisor), School of Interactive Computing, Georgia Institute of Technology

Dr. Jennifer Hammock, National Museum of Natural History, Smithsonian Institution

Dr. Robert J. Moore, IBM Research-Almaden

Dr. Spencer Rugaber, School of Interactive Computing, Georgia Institute of Technology

Dr. Sashank Varma, School of Interactive Computing, Georgia Institute of Technology

Dr. Emily Weigel, School of Biological Sciences, Georgia Institute of Technology



Systems thinking is a useful skill for addressing ill-defined problems in complex domains. Yet, robust computational models of how adult learners engage in systems thinking or how to help them learn about systems thinking in a self-directed manner are not available. In this interdisciplinary work, I use theories and techniques from cognitive science, learning science, artificial intelligence, and data mining to develop a computational model of self-directed adult learning about systems thinking in the domain of ecology.


To achieve this goal, I present the Virtual Experimentation Research Assistant (VERA; vera.cc.gatech.edu)-- an interactive learning environment that enables learners to access large-scale biological knowledge from Encyclopedia of Life (EOL), construct conceptual mechanistic models of ecological systems, run agent-based simulations of these models, and revise the models and simulations as needed. I have used VERA to complete two preliminary field studies. The first study explored the effects of modeling in acquiring domain knowledge. I found that engaging in ecological modeling using VERA helped college-level students acquire biological knowledge, and access to large-scale domain knowledge helped them construct more complex models and develop a larger number of hypotheses for a given problem. The second study investigated novice learners’ behaviors in estimating the parameters for agent-based simulations. I discovered that students showed multiple cognitive strategies for parameter estimation such as systematic search, problem reduction/decomposition, global/local search.

VERA is now accessible through Smithsonian Institution’s EOL website (eol.org) and it is used by thousands of self-directed learners around the world. To complete my dissertation, I plan to conduct two additional studies. The first will use data mining techniques to understand patterns in how self-directed adult learners use VERA to construct models to address ill-defined problems. The second study will explore the effects of using VERA in self-directed learning by comparing the students’ modeling behaviors and learning outcomes in guided and self-directed learning. Together these four studies will lead to a computational model of how adult learners learn about systems thinking in a self-directed manner and how to design interactive learning environments to support self-directed systems thinking in open and ill-defined problems.


  • Workflow Status:Published
  • Created By:Tatianna Richardson
  • Created:11/22/2021
  • Modified By:Tatianna Richardson
  • Modified:11/22/2021