A Visual Approach towards Knowledge Engineering and Understanding How Students Learn in Complex Environments

Exploratory learning environments, such as virtual labs, support divergent learning pathways. However, due to their complexity, building computational models of learning is challenging as it is difficult to identify features that (i) are informative with respect to common learning strategies, (ii) abstract similar actions beyond surface differences, and (iii) differentiate groups of learners. In this paper, we present a visualization tool that addresses these challenges by facilitating a novel analytic approach to aid in the knowledge engineering process, focusing on five main capabilities: data-driven hypotheses raising, visualizing behavior over time, easily grouping related actions, contrasting learners' behaviors on these actions, and comparing the behaviors of groups of learners. We apply this analytic approach to better understand how students work with a popular interactive physics virtual lab. By splitting learners by learning gains, we found that productive learners performed more active testing and adapted more quickly to the task at hand by focusing on more relevant testing instruments. Implications for online virtual labs and a broader class of complex learning environments are discussed throughout.