A Framework for Online Learning Analytics in K-12 Classrooms as a Precursor for Personalized Learning: Emergent Practices in Schools

Introduction

Learning Analytics (LA) involve “the measurement, collection, analysis, and reporting of data about learners and their contexts, … and the environments in which it occurs” (Siemens, 2013, p. 1382), “in order to understand and” optimize learning (Ferguson, Clow, Griffiths, & Brasher, 2019, p. 43). As a rapidly growing field, LA is identified as a ‘midterm horizon’ for education (New Media Consortium, 2015), since many educational institutions have been using LA, albeit scarcely, and mostly through small-scale projects (Siemens, Dawson, & Lynch, 2013). Beyond question, LA research as a field embarks and draws on data gathered, analyzed and reported about and “from learners’ interactions with educational technologies” and learning environments “to provide information and insights into” their learning (Lim, Dawson, Joksimovic, & Gašević, 2019, p. 250) in order to benefit from the potential of digital footprints (Siemens & Gašević, 2012).

In doing so, data science methods are utilized “with the goal to harness vast amounts of data about learning collected by the extensive use of” technologies (Gašević, Kovanović, & Joksimović, 2017, p. 63) to evaluate such data and present the findings in a myriad of textual and visual formats. Given the growing interest in this research field and practice, LA had matured into a rich praxis for many disciplines (Li & Wong, 2019) with promising results in order to shape pedagogical shifts, feasible allocation of institutional resources, and retention strategies that students can employ (Gašević, Dawson, & Siemens, 2015; Lim, et al., 2019). The journal article by Gašević, et al. (2015, p. 64) first introduced “the field of learning analytics and” outlined some of the lessons learned. Thus, like that of the edited book that it proposes to form part of, the target audience of this chapter will be composed of professionals, educators and researchers working in the field of education, together with “graduate students in education who used to be (or are planning to become) educators, teachers, school administrators”, etc., who might “have little to no technical background” (Schneider, Reilly, & Radu, 2020, p. 91). The research findings of Avella, Kebritchi, Nunn, and Kanai (2016) implored educational stakeholders, who work with data, to have the relevant training in learning analytics and be able to understand how to apply the data effectively to achieve meaningful results.