Shape of Educational Data

Funded by NSF’s Research on Education and Learning (REAL) program, this grant for exploratory research applies advanced topological, geometric, and Bayesian methods to analyze the shape of data generated by students taking mathematics courses via massive open online course (MOOC) systems. This project links data analyses from three leading learning platforms in the service of better understanding student learning in mathematics. For example, one facet of this project is to examine the psychological factors (e.g., math anxiety, spatial skills) that help us understand the ways that students navigate through materials in online courses as well as how well they perform in the courses. This line of work has the potential to fundamentally change the way we think about assessment data in support of mathematics learning and perhaps other STEM content.

Further, the project will seed a new community of researchers across disciplines that typically do not interact (e.g., mathematics, educational psychology, computer science). We will host a 3-day meeting to bring leaders in the mathematical community, who are experts in topology and geometry, to work with researchers who run learning platforms that collect massive amounts of data on how students learn, and those with related expertise (e.g., educational psychologists). After this meeting, proceedings will be available online to researchers interested in this area.