Using Algorithmic Understanding of Student Comprehension of Computer Science Concepts to Support Teachers with Personalized Student Recommendations

In a previous project, the company developed a high school-level computer science intervention (2 Sigma Schools) for remote teaching and learning with live and pre-recorded lectures describing hands-on activities and online exercises. During Phase In in 2022, the team developed a prototype of a machine learning dashboard to track student learning progressions and generate fine-grained pedagogical recommendations that educators can use to inform practice. At the end of Phase I, a pilot study with four educators and 250 high school students demonstrated that the prototype functioned as intended, and that the machine learning component generated information that educators found useful for providing individualized information on each student.

In Phase II of the project, the research team will fully develop the product, including a data visualization dashboard, a competition platform, and ten classroom instructional modules. Iterative refinements will be conducted with feedback from educators and students at major production milestones until the product is fully functional. After development concludes, a pilot study will test the feasibility and usability, fidelity of implementation, and the promise of the product for improving computer science learning. The team will collect data from 30 middle school science classes, with half randomly assigned to use the product and the other half to use business-as-usual activities for the same course content. Researchers will compare pre-and-post scores for computer science learning. Researchers will gather cost information using the "ingredients method" and will include all expenditures on things such as personnel, facilities, equipment, materials, and training.