III: Small: DataWorld: Externalizing Hidden Data Flows for Anywhere Analytics
Understanding data from everyday life could help professionals, policymakers, and citizens make our society better, fairer, and more efficient. For example, imagine hunting for a house by walking through the neighborhood in which you want to live and discovering facts about the area from social media, census data, and nearby schools. Alternatively, imagine an architect showing her clients a new office building in its actual location in the city with the wandering sun, ebb and flow of crowds, and waves of car traffic as a backdrop. However, most of collected information cannot be accessed and integrated based on geographical space. This project will investigate how to bridge data and the world from where it was collected by adding visualizations that will make the underlying data visible in the real world by using Augmented Reality (AR). This will help people use the massive troves of data on the internet by literally putting it at their fingertips as part of the world around them. The project will be deployed on a university campus to help students, faculty, and visitors tune in to its “heartbeat” of events, alerts, and historical background. Finally, the project will also engage students in refining and contributing to the database, help attract underrepresented students to computing careers, and build a community of researchers interested in the combination of data and geographical place.
To achieve these goals, this project will build a framework called DataWorld for creating situated data streams and externalizing them using AR technology. In effect, this will blend the real world with the hidden world of data. This framework will both combine existing data from a wide variety of sources, such as social media, public databases, and popular websites, as well as enable grassroot contributions from DataWorld users. This framework will then be applied to three separate themes. (1) Public safety, where information about crime, emergencies, and current events can help users. (2) History awareness, where the situated data streams will be used to reveal the footsteps of those who came before us, such as placing old newspaper stories in their geographical context, highlighting the struggles — large and small — of the civil rights movement, and showing urban development in situ over time. (3) Civic awareness, where the situated data streams can disseminate information about current events, promote sustainability and environmentally-conscious behavior, and facilitate crowdsourced data collection at a grassroots level, fostering a form of “virtual” geocaching where data can be hidden in the world. These applications will not only provide new techniques and frameworks that contribute to our knowledge of situated data, data visualization, and Augmented Reality, but will be deployed in practice using the University of Maryland campus as a testbed. The project will generate one or several DataWorld apps, both for handheld devices as well as head-mounted displays, that will enable both contributing grassroot data to the DataWorld platform as well as viewing the data in situ. At the end of the project, an anonymized version of the DataWorld database will be published. Finally, educational material, source code, and documentation will also be released as open source during the project.
This award reflects NSF’s statutory mission and has been deemed worthy of support through evaluation using the Foundation’s intellectual merit and broader impacts review criteria.
August 2019 - August 2022
- Machine Learning, AI, Computational Linguistics, and Information Retrieval
- Data Science, Analytics, and Visualization
- Information Justice, Human Rights, and Technology Ethics
- Library and Information Science
Total Award Amount: