PhD Project: Optimizing Personalized Learning at Scale by Setting up Failure for Success

Big online data is increasingly valuable in the study of latent cognitive processes. In the field of educational psychology, the heightened popularity of online learning environments (OLEs) invites new avenues for studying and promoting learning. OLEs provide large-scale educational data; the platform Prowise Learn, for example, contains responses from hundreds of thousands of students across more than a decade — a unique opportunity to study learning processes that are harder to detect in traditional lab studies.

This project promotes success in learning by investigating its counterpart: failure. Failure-related behavior, such as making errors, can inform educational measurement and personalized learning algorithms. Research questions include:

• What causes underlie errors? We use the Systematic Error Tracing Algorithm to detect which misconceptions likely lead to individuals' error responses.
• What are the consequences of errors? We extend recent findings that sequential errors predict quitting, and relate this to problem-skipping behavior.
• Is there individual variability? We find student-specific factors that can be targeted to improve each student's learning process.
• Intervention research: We conduct A/B tests to causally determine the impact of investigated factors on student success.

This project runs from 2023 to 2027 and is supervised by Alexander Savi, Abe Hofman, and Han van der Maas at the University of Amsterdam.