New Experiment in the Field: AI-powered Adaptive Learning

On July 15th a new intervention that is joined work with Marius Köppel, Daniel Schunk, and Isabell Zipperle went live. We want to find whether the predictive power of a convolutional neural network can take adaptive learning to the next level. In prior work with Daniel Schunk we found that optimizing the difficulty of tasks with a nearest-neighbor-based predictive algorithm increased learning effort, but individualization did not. Can AI beat this?

This is our preliminary abstract: It remains an open question how to adapt and individualize learning contents. To tackle this in a digital learning context, we developed an algorithm based on a convolutional neural network that assigns tasks to the learners. Our application is a large online learning platform in which we run a randomized controlled trial. Participants are randomized into three groups: two treatment groups – a group-based adaptive treatment group and an individualized adaptive treatment group – and one control group. We analyze the difference between the three groups with respect to effort learners provide within the platform, their performance within the platform, formative assessments within the platform and their final high-stake standardized exams (summative assessment).

We pre-registered the experiment at the AEA RCT Registry.

Leave a Reply