Abstract

Context: Conceptual developments in our understanding of knowledge are merging with machine-learning methods for making sense of data. This creates new, and interesting ways in which we can document and analyse knowledge, and conceptual change. Problem: Currently, the study of conceptual change is often limited to small sample sizes because of the laborious nature of existing, purely qualitative approaches. Method: We present Association Rule Mining to better measure and understand changes in students’ thinking at the classroom level, based on data collected while implementing a constructionist learning activity in a US college classroom. Association Rule Mining is used on a set of qualitatively coded student responses. We then look at changes in the association rules between students’ responses before and after a learning activity to better understand students’ conceptual change at the classroom level. Results: We find that students converge on a more complete and accurate set of causal claims in their post-responses. Finding these changes would have been difficult or impossible without Association Rule Mining, or a similar approach. This suggests that Association Rule Mining is a potentially fruitful approach to analysing conceptual change at the classroom level. Implications: Adding Association Rule Mining to the arsenal of computational qualitative methods will let us study student data of larger sizes than previously. Constructivist content: Association Rule Mining is agnostic with regard to the ontology of its data. This makes Association Rule Mining a particularly suitable analysis method when taking a constructivist view of learning.