EAGER: News and Public Affairs Information

This project tests theories of reinforcement to view high-quality balanced news and public affairs information. This project develops two robust and principled interventions that nudge social media algorithms to influence news and public affairs recommendations. This project is supported under the EAGER program to encourage high risk, high reward research.

The project team is designing, developing, and testing a personalized reinforcement learning based intervention that considers a user’s past watch history and incorporates explicit user feedback to further adapt intervention to user preferences. The project team is comparing this tool with is a generic “one size fits all” intervention, which obfuscates the watch history.

The system design includes a method for identifying quality news (using validated expert metrics). The effectiveness of each tool is being evaluated in systematic, controlled sock puppet-based experiments.

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.