Identifying Students' Inquiry Planning Using Machine Learning

This research investigates the detection of student meta-cognitive planning processes in real-time using log tracing techniques. We use fine and coarse-grained data distillation, in combination with coarse-grained text replay coding, in order to develop detectors for students’ planning of experiments in Science Assistments, an assessment and tutoring system for scientific inquiry. The goal is to recognize student inquiry planning behavior in real-time as the student conducts inquiry in a micro-world; the eventual goal is to provide realtime scaffolding of scientific inquiry.