ECR Betty’s Brain-BROMP
Modeling Self Regulated Learning with Betty’s Brain
The primary goal for this project is to enhance the theory and measurement of students’ self-regulated learning (SRL) processes during science learning by developing a technology based framework which leverages human expert judgment and machine learning methods to identify key moments during SRL and analyze these moments in depth.
These issues are being studied in the context of Betty’s Brain, an open-ended science learning environment that combines learning-by-modeling with critical thinking and problem-solving skills to teach complex science topics.
We are developing a novel measurement framework that will identify key inflection points in learners’ SRL processes that drive their cognition, metacognition and affect, and inform researchers about these inflection points in real time, so that the researchers can conduct observations and interviews right at the critical moments when the change is occurring. The results of this data collection will be integrated with sequential pattern mining to drive the refinement and extension of an existing theory of SRL (Winne’s COPES framework) to increase its specificity and predictive power.
- Analysis of data on student performance, behavior, affect and goal orientation collected during Study 1 (March 2017 – four 6th grade classrooms of Meigs Academic Magnet Middle School, Nashville, TN)
- Building and refining of automated detectors for affect, cognition, metacognition, and SRL behaviors (feature engineering and deep learning approaches)
- Design of Study 2, including –
- development of a new android app that will notify classroom researchers of key inflection points in the cognitive, metacognitive, and SRL behaviors of students as detected in real time
- Development of the app-server-clients communication framework
- Pilot study (May 2018 – Jere Baxter Middle School, Nashville, TN) to test this newly developed framework in a classroom setting)
University of Pennsylvania: Prof Ryan Baker, Jaclyn Ocumpaugh, Yang Jiang, Stefan Slater
University of Illinois at Urbana-Champaign: Prof Luc Paquette, Nigel Bosch
External collaborator for QRF app design: Martin van Velsen
- Betty’s Brain,
- HART (android app used for collecting BROMP data),
- QRF (android app for study 2 – under development)
- Munshi, A., Rajendran, R., Moore, A., Ocumpaugh, J., & Biswas, G. (2018). Studying the Interactions between Components of Self-Regulated Learning in Open Ended Learning Environments. In Proceedings of the 13th International Conference of the Learning Sciences (ICLS), London.
- Munshi, A., Rajendran, R., Ocumpaugh, J., Biswas, G., Baker, R. S., & Paquette, L. (2018). Modeling Learners Cognitive and Affective States to Scaffold SRL in Open Ended Learning Environments. In Proceedings of the International Conference on User Modelling, Adaptation and Personalization (UMAP), Singapore.
- Jiang, Y., Bosch, N., Baker, R. S., Paquette, L., Ocumpaugh, J., Andres, J. M. A. L., Moore, A. L., & Biswas, G. (2018) Expert feature-engineering vs. deep neural networks: Which is better for sensor-free affect detection?. In U. Hoppe, C. Rosé, & R. Martinez (Eds.), Proceedings of the 19th International Conference on Artificial Intelligence in Education (AIED 2018). Berlin Heidelberg: Springer-Verlag.