Learning Analytics for Process-driven Computer Programming Assignments
Effective Years: 2023-2026
To develop student skills in computer programming, it is essential to understand how students approach computer programming assignments. This knowledge can improve teaching techniques, foster a diverse and inclusive student body, and enhance our Nation's digital proficiency. This project at Utah State University seeks to investigate students' keystroke patterns as they work on Python programming assignments in introductory computer programming courses. This innovative approach provides educators with actionable insights that could improve computer science education. By analyzing academic and demographic data, as well as controlled exercises, this project aims to develop targeted intervention strategies that help struggling students succeed, while also developing education research skills. The ultimate goal is to promote scientific advancement and strengthen the Nation's computer science expertise, contributing to national prosperity and welfare. This project has far-reaching implications, potentially impacting not just current students but also our Nation's digital capabilities and resilience in the years to come.
The rapid advancements in educational technology have presented an exceptional opportunity to collect intricate details about students' learning processes across various activities. The surge in computer-based learning has further accelerated the collection of rich, granular data from students. In this project, these advancements are leveraged to conduct a pilot project focused on enhancing the pedagogy of introductory computer programming. The project's first phase seeks to focus on the construction of a student dataset that will encapsulate student programming keystrokes, demographic and academic characteristics, as well as controlled exercises. Two innovative techniques to examine student coding behavior through the dual lenses of computational thinking and cognitive processes will be implemented. This project aims to culminate in the development of an advanced and interpretative machine learning model that will be able to predict student outcomes and detect plagiarism. The insights from this pilot project will be disseminated among instructors and practitioners, empowering them to formulate effective intervention strategies. The proposed research activities are meticulously designed to bolster the PI's capacity. They will equip the PI with broad knowledge, skills, and expertise, fostering professional development in this dynamic field. This project is supported through a partnership with the Bill & Melinda Gates Foundation, Schmidt Futures, and the Walton Family Foundation. This project is also supported by NSF's EDU Core Research Building Capacity in STEM Education Research (ECR: BCSER) program, which is designed to build investigators' capacity to carry out high-quality STEM education research in the core areas of STEM learning and learning environments, broadening participation in STEM fields, and STEM workforce development.
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.