Making Bigger Waves: Automating Theoretical Coding to Generate Educationally Meaningful Learning Analytics

Education is offering evermore possibilities for generating learning analytics. However, to ensure that patterns revealed by analysing large-scale data are meaningful for education and to determine their educational implications requires educational theories. This chapter draws on a framework already having significant impact in education: Legitimation Code Theory (LCT). Like other educational theories, LCT is limited by its reliance on time-intensive manual analysis. Unlike many other theories, LCT concepts have clear empirical referents, lending themselves to automation. In this chapter we describe a pilot study to automate theoretical coding, using a concept from LCT that explores changes in the complexity of knowledge being expressed in, for example, classroom discourse and student assessments. First, we introduce LCT and why its concepts lend themselves to automation. Second, we outline how, through manual analyses and machine learning, we iteratively trained and tested an algorithm to support research using a specific concept. Third, we discuss a prototype visualization of results offered by the resulting automated analysis. Our aim is to show educational scholars how automated support for their analyses is within reach and to illustrate to learning analytics scholars how proven educational theories may offer a powerful resource to create meaningful and actionable insights.