Collaborative research: georelational dynamics in collective action

Carnegie Mellon University received a $200,934 Project Grant from the National Science Foundation (NSF) Division of Social, Behavioral, and Economic Science (CFDA 47.075) awarded September 15, 2025, to develop the GeoRelational Dynamics (GEORDyn) Toolkit. This collaborative research initiative leverages advances in artificial intelligence, computer science, and statistics to create methodological tools that enable researchers to analyze spatial and relational complexities in collective action events. The toolkit addresses longstanding research questions regarding network emergence, influence on collective action, and event diffusion across time and space by providing dynamic methods and software capable of handling complex dependencies at micro, meso, and macro analytical levels. The resulting toolkit will serve both academic researchers and external stakeholders requiring rigorous causal inference capabilities for understanding causes and implications of complex events.

The project, scheduled for completion by August 31, 2027, includes a planned sub-award to the Atlantic Council of the United States to support a virtual workshop scheduled for February 6, 2026. This workshop will convene researchers and practitioners to discuss preliminary project findings, evaluate the toolkit's application to alternative contexts and cases, and identify follow-on research opportunities and collaborative projects emerging from workshop participants. This engagement strategy ensures dissemination of project outcomes and builds pathways for sustained research utilization beyond the initial grant period.

Abstract

This project uses advances in artificial intelligence, computer science, and statistics to develop the geordyn toolkit to allow researchers to identify the spatial and relational complexities in more fine-grained data. This will permit new approaches to investigating longstanding questions in the field, such as if and how networks emerge and influence collective action and the conditions under which events diffuse across time and space. Events are often observed at different temporal and spatial scales, involving complex interactions among actors at the micro, macro, and meso levels. Methodological tools commonly used in the study of collective-action events are often less dynamic and/or do not account for complex dependencies. This project develops the geordyn toolkit to help researchers dissect the spatial and relational complexities in events and draw rigorous causal inferences. The toolkit incorporates recent advances in artificial intelligence (AI), computer science, and statistics. The project develops new methods and software for studying complex and dynamic processes, such as diffusion, that can be used by researchers as well as those outside of the academic community who need to understand the causes and potential implications of events. 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.- subawards are planned for this award.