Project Grant 2624833

The National Science Foundation Division of Research on Learning in Formal and Informal Settings awarded University of Wisconsin–Madison $749,557 on August 15, 2026, under the STEM Education program (CFDA 47.076) to develop a freely available educational game that teaches middle school students artificial intelligence literacy through narrative-driven gameplay.

The project will create a learning game co-designed with educators, students, game designers, and AI researchers that makes foundational AI concepts—particularly classification processes underlying recommendation systems, facial recognition, spam filters, and social media platforms—accessible to middle school learners with varied interests and learning approaches. The game will be distributed to classrooms across the United States.

The research investigates how five dimensions of narrative design influence student outcomes: choice structure, character richness, narrative richness, learning-agent competency, and setting realism. Students will complete brief assessments of their values and interests; the game will collect detailed interaction data to determine which narrative configurations best support learning, engagement, and enjoyment across different learner profiles. The evaluation approach combines embedded assessment, educational data mining, large-scale gameplay analysis, and computational optimization to test many narrative configurations efficiently. The project will also produce design knowledge to guide development of future educational games across STEM topics.

Work is performed in Madison, Wisconsin, with a performance period ending July 31, 2029.