In spite of decades of use of agent-based modelling in social policy research and in educational contexts, very little work has been done on combining the two. This paper accounts for a proof-of-concept single case-study conducted in a college-level Social Policy course, using agent-based modelling to teach students about the social and human aspects of urban planning and regional development. The study finds that an agent-based model helped a group of students think through a social policy design decision by acting as an object-to-think-with, and helped students better connect social policy outcomes with behaviours at the level of individual citizens. The study also suggests a set of new issues facing the design of Constructionist activities or environments for the social sciences.

Key words: agent-based modelling, NetLogo, social policy education, constructionism.

Abstract: Designing, implementing and assessing the effects of classroom-based learning experiences spans across a wide variety of methodological, epistemological and design-related issues. Additionally, the use of data mining and computational methods for supporting qualitative data analyses is still new to the field. Potentially because of this, we received ten good, but quite different commentary questions, which we have organized under five headings. In this response, we address each of them to provide a more thorough background or reasoning behind the decisions we made in our target article.

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

Key words: Qualitative research, computational methods, knowledge analysis, education, conceptual change, complex systems thinking, learning sciences, constructionism.

The goals of instruction are usually taken to be fixed, at least in their broad outline. Forexample, in elementary school mathematics, students progress from counting to addition,multiplication, and fractions. Given this state of affairs, the business of educational researchhas been to determine how the fixed instructional aims can best be reached. Educationresearchers have traditionally asked questions such as: What are the typical difficulties thatstudents experience? Which means of instruction – method A or method B – is better forachieving our instructional aims? In contrast, we will describe a line of work in which we have shifted the focus from themeans to the object of learning. We are concerned with how the structure and properties ofknowledge affect its learnability and the power that it affords to individuals and groups. Webriefly review three agent-based restructurations of traditional science content and discuss the consequences for scientific power and learnability.