NLP Assist: Natural Language Processing in STEM Education Research

Humans trained in education research have long been considered the sole experts in interpreting learning and the quality of learning environments. But when such judgement relies on the interpretation of text, the process can be slow and labor intensive, thereby limiting how quickly and effectively educators can respond to changing student needs. While natural language processing (NLP) cannot replace human interpretation, recent advances now allow it to be strategically integrated with human insight to enable more comprehensive and objective models of student learning with remarkable fidelity. These same technologies are already transforming the understanding and prediction of cognition in psychology and related social sciences. The Natural Language Processing in STEM Education Research Institute (NLP Assist) will increase the capacity of individuals invested in STEM education to understand student learning, explore teacher experiences, and ultimately support high quality learning that keeps pace with changes in societal priorities and student needs. The Institute will train approximately 120 STEM education researchers—graduate students, faculty, postdoctoral researchers, and research staff—from universities and nonprofits in applying NLP to their areas of research. Training will combine proven teaching and organizational methods and include a 2-day in-person immersion, an eight-week online workshop series, and mini-sessions at national conferences. Participants will gain hands-on experience using Python and AI tools to analyze qualitative, textual data, supported by pre-workshop preparation and post-workshop mentoring. Throughout the program, participants will engage in a Slack-based peer community, receive individualized support through monthly check-ins and 1:1 troubleshooting, and join a growing network committed to advancing STEM education through innovative, data-driven research. The project is 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. The project is also supported through a collaborative NSF activity with the Bill & Melinda Gates Foundation, Schmidt Futures, and the Walton Family Foundation. 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.