EAGER: Hybrid human-AI technologies for forecasting trends.

Pennsylvania State Univ University Park, University Park PA

Investigators

Abstract

This EAGER project is developing hybrid (human-AI) technologies for forecasting complex sociotechnical outcomes. The project considers community experiences of social media as a proving ground for design and development. In doing so, it is laying theoretical and empirical groundwork for future technologies supporting user governance in shared spaces online. The project’s research has the main objectives of advancing machine learning and artificial intelligence to support the integration of human inputs through hybrid prediction markets, wherein humans participate alongside bot of AI-enabled traders to buy and sell assets representing future outcomes and deploying hybrid prediction markets to forecast user experiences, perspectives, and narratives online. This project is the first comprehensive effort to build and test hybrid prediction markets for integrated human-AI forecasting, and thus is a high risk-high reward EAGER effort. The approach will fold in human input as other machine learning algorithms cannot, i.e., directly within the algorithm's deployment, showcasing an opportunity for the integration of first-person perspectives and machine learning for complex tasks where participatory design is desirable. Markets will be studied theoretically and in practice, and thoroughly compared against a suite of computational, crowdsourced and hybrid benchmarks, including supervised and semi-supervised algorithms, survey elicitation, and ensembling. The market approach could enable explanations not generally afforded by deep learning-driven approaches yet critical to platforms and policy makers. Design of hybrid technologies will build on the first-hand accounts of impacted individuals and development will engage with community members throughout. 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.