Collaborative Research: Learning probability through AI problem-solving in a Game-based Environment

Understanding probability is essential for daily life. Probabilistic reasoning is critical in decision making not only for people but also for artificial intelligence (AI). AI sets a modern context to connect probability concepts to real-life situations.

It also provides unique opportunities for reciprocal learning that can advance student understanding of both AI systems and probabilistic reasoning. This project aims to improve the current practice of high school probability education and to design AI problem-solving to connect probability and AI concepts. Set in a game-based environment, students learn and practice applying probability theory while exploring the world of probability-based AI algorithms to solve problems that are meaningful and relevant to them.

The project holds significant potential for advancing our knowledge on how to support youth in gaining knowledge while targeting misconceptions of probability, as well as addressing the urgent need of helping the nation’s youth learn the fundamentals of AI. The project will be piloted in classrooms in the Local District East of the Los Angeles Unified School District.

Through a partnership with the Viterbi K-12 STEM Center at the University of Southern California, the project plans for broad dissemination of the technology and findings, including the game-based learning environment and teacher professional development resources.

The project aims to use technology-supported learning to improve current practice in high school math education through research and development of a game-based learning environment. The project will engage teachers as co-designers to develop AI problem-solving based on the high school probability curriculum, and iteratively refine the problem design through cognitive interview studies.

Building on the instructional guidelines and scaffolding strategies distilled from these studies, the project will develop a game-based learning environment that will guide students through problem-solving based learning, address students’ misconceptions in probability, immerse them in scenarios aligned with the interests of the students and mirror those in real-life where the probability concepts and AI algorithms can be applied. Through a series of pilot studies and scaled-up studies, the project will iteratively refine the game-based learning environment and gather evidence of how and how well students learn through the game, measured through objective performance, motivations, and transfer.

Additionally, the project will gather feedback from the teachers through professional development workshops and pilot studies, to understand how teachers use the game in classroom teaching. This project is supported by NSF's Discovery Research PreK-12 (DRK-12) program, in the Directorate for Education & Human Resources. DRK-12 seeks to significantly enhance the learning and teaching of science, technology, engineering and mathematics (STEM) by preK-12 students and teachers through research and development of innovative resources, models and tools.

Projects in the DRK-12 program build on fundamental research in STEM education and prior research and development efforts that provide theoretical and empirical justification for proposed projects. This project is also co-funded by the Innovative Technology Experiences for Students and Teachers (ITEST) program, which supports projects that build understandings of practices, program elements, contexts and processes contributing to increasing students' knowledge and interest in science, technology, engineering, and mathematics (STEM) and information and communication technology (ICT) careers.

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.