Identifying struggling students in real-time provides a virtual learning environment with an opportunity to intervene meaningfully with supports aimed at improving student learning and engagement. We present a detailed analysis of quit prediction modeling through interaction log data of students playing a learning game called Physics Playground. Next, we study epistemic networks from five game levels to study how the temporal interconnections between the events are different for students who quit the game and those who did not to understand why students quit a level in the game.
Data - Interaction log, on-screen sketches, qualitative codes, affect predictions
Methods - Machine learning, epistemic network analysis
Karumbaiah, S., Baker, R.S., Shute, V. (2018) Predicting Quitting in Students Playing a Learning Game. Proceedings of the 11th International Conference on Educational Data Mining (EDM). [pdf] Nominated for Best Paper Award
- Karumbaiah, S., Baker, R.S., Barany, A., Shute, V. (2019) Using Epistemic Networks with Automated Codes to Understand Why Players Quit Levels in a Learning Game. Proceedings of the International Conference on Quantitative Ethnography (ICQE). [pdf]
- Karumbaiah, S., Rahimi, S., Baker, R.S., Shute, V., D’Mello, S.K. (2018) Is Student Frustration in Learning Games More Associated with Game Mechanics or Conceptual Understanding? Proceedings of the 13th International Conference of the Learning Sciences (ICLS). [pdf]