Detecting the Moment of Learning

Ryan S. J. d. Baker, Adam B. Goldstein, Neil T. Heffernan

Intelligent tutors have become increasingly accurate at detecting whether a student knows a skill at a given time. However, these models do not tell us exactly at which point the skill was learned. In this paper, we present a machine-learned model that can assess the probability that a student learned a skill at a specific problem step (instead of at the next or previous problem step). Implications for knowledge tracing and potential uses in “discovery with models” educational data mining analyses are discussed, including analysis of which skills are learned gradually, and which are learned in “eureka” moments.

The final publication is available at Springer via