Putting the individual first: Capturing individual differences in feedback processing during educational tasks

Every day, millions of children across the world use e-learning platforms to support their education. One of the central innovations is that these platforms are almost universally adaptive: each child generally encounters items suitable to their current ability. However, an equally central component of these learning platforms is not adapted to individual differences: The nature of the feedback children receive.

Almost every platform implements some form of feedback: a child is shown whether they answered a given item correctly, resulting in either positive (reward) or negative (loss) feedback through in-game rewards. Current feedback systems are a) often the same for all children b) do not distinguish positive from negative feedback and c) use deterministic feedback (4,5). This is a missed opportunity for children, educators, and parents alike. Optimizing reward administration across platforms and individuals has the evidence-based potential for translational payoffs including boosting engagement, retention, attention and learning.

This project will integrate knowledge about feedback learning with computational modeling. This team will examine whether children respond differently to feedback across a range of tasks. If successful, this project will lay the foundation for future projects which implement knowledge about feedback-based learning processes to individualize and optimize the nature of feedback in learning platforms.