Recent advances in multimodal learning analytics show significant promise for addressing these challenges by combining multi-channel data streams from fully-instrumented exhibit spaces with multimodal machine learning techniques to model patterns in visitor experience data. We describe initial work on the creation of a multimodal learning analytics framework for investigating visitor engagement with a game-based interactive surface exhibit for science museums called Future Worlds.
DATE:
TEAM MEMBERS:
Jonathan RoweWookhee MinSeung LeeBradford MottJames Lester
resourceresearchMuseum and Science Center Exhibits
Multimodal models often utilize video data to capture learner behavior, but video cameras are not always feasible, or even desirable, to use in museums. To address this issue while still harnessing the predictive capacities of multimodal models, we investigate adversarial discriminative domain adaptation for generating modality-invariant representations of both unimodal and multimodal data captured from museum visitors as they engage with interactive science museum exhibits.
DATE:
TEAM MEMBERS:
Nathan HendersonWookhee MinAndrew EmersonJonathan RoweSeung LeeJames MinogueJames Lester
resourceresearchMuseum and Science Center Exhibits
Recent years have seen a growing interest in investigating visitor engagement in science museums with multimodal learning analytics. Visitor engagement is a multidimensional process that unfolds temporally over the course of a museum visit. In this paper, we introduce a multimodal trajectory analysis framework for modeling visitor engagement with an interactive science exhibit for environmental sustainability.
DATE:
TEAM MEMBERS:
Andrew EmersonNathan HendersonWookhee MinJonathan RoweJames MinogueJames Lester
resourceresearchMuseum and Science Center Exhibits
In this paper, we introduce a Bayesian hierarchical modeling framework for predicting learner engagement with Future Worlds, a tabletop science exhibit for environmental sustainability.
DATE:
TEAM MEMBERS:
Andrew EmersonNathan HendersonJonathan RoweWookhee MinSeung LeeJames MinogueJames Lester
resourceresearchMuseum and Science Center Exhibits
In this paper, we investigate bias detection and mitigation techniques to address issues of
algorithmic fairness in multimodal models of museum visitor visual attention.
DATE:
TEAM MEMBERS:
Halim AcostaNathan HendersonJonathan RoweWookhee MinJames MinogueJames Lester
resourceresearchMuseum and Science Center Exhibits
This poster was presented at the 2021 NSF AISL Awardee Meeting.
Project Harvest is a co-created citizen science project that investigates the quality of household environments in Arizona communities neighboring active or legacy mining and/or toxic release. Project Harvest is a response to the community-driven questions, “Are there pollutants in harvested rainwater? Can I use the harvested rainwater for my garden?"
The attached Briefing Booklet was created collaboratively by A2A (Awareness to Action) Planning Workshop facilitators and organizers in advance of the February 2018 convening and was available to participants.
The workshop's primary goal was to establish an operational strategy for knowledge sharing across entities, networks, and associations designed to strengthen communities of practice nationally to better conceive, conduct, and evaluate projects for the public, working at the intersection of science, arts, and sustainability.
The booklet contains an overview of the workshop purpose
In The Nature of Community: SCIENCES, we share the lessons learned from an innovative partnership designed to leverage the strengths of two nonprofit organizations—a large cultural institution and a smaller, deeply-rooted community-based organization, both of which offer informal science education expertise.
You’ll read first-hand reflections of how staff members, community leaders and members, children, and adults experienced this partnership: the expectations, surprises, challenges, successes, and lessons learned. We hope the description of this partnership inspires other organizations to