Early Prediction of Conceptual Understanding in Interactive Simulations

Interactive simulations allow students to independently explore scientific phenomena and ideally infer the underlying principles through their exploration. Effectively using such environments is challenging for many students and therefore, adaptive guidance has the potential to improve student learning. Providing effective support is, however, also a challenge because it is not clear how effective inquiry in such environments looks like. Previous research in this area has mostly focused on grouping students with similar strategies or identifying learning strategies through sequence mining. In this paper, we investigate features and models for an early prediction of conceptual understanding based on clickstream data of students using an interactive Physics simulation. To this end, we measure students’ conceptual understanding through a task they need to solve through their exploration. Then, we propose a novel pipeline to transform clickstream data into predictive features, using latent feature representations and interaction frequency vectors for different components of the environment. Our results on interaction data from 192 undergraduate students show that the proposed approach is able to detect struggling students early on.