PIs: Leilah Lyons, Stephen Uzzo
New York Hall of Science
Award Details

Museums are increasingly developing digital learning experiences where visitors generate interesting usage data, but these data are rarely used to support learning. This project poses a “human-in-the-loop” model of facilitation where museum experts are provided with data visualizations and other feedback derived by mining exhibit use data. These visuals will be used as coaching support for facilitators as they help visitors make sense of the rich learning experiences that digital exhibits now offer. While this approach is immediately relevant to museum learning, human-in-the-loop systems represent a new take on cyberlearning systems that will be applicable to many other formal and informal STEM learning environments that demand immediate, just-in-time reflection that is guided by an expert observer.

The intervention will be used in the context of an open-ended, participatory exhibit that invites up to 50 visitors at a time to manipulate a simulated ecosystem, with the goal of having visitors engage with concepts related to sustainability and complex systems by exploring emergent phenomena. Open-ended learning experiences are common to museum exhibits but are under-studied in the Educational Data Mining (EDM) community. This research will add to the growing EDM literature on open-ended problems and provide insights for how museum exhibits can be designed to supply data that can be useful for analytics and data mining. A goal of this research is to develop and refine a typology of the forms of information that museum and other facilitators working with real-time data can make sense of and act on, which could be used to inform both the analytics and the software design for future tools to facilitate learning.