Designing Online Learning Strategies through Analytics

Introduction

We live in an increasingly digital era, defined by information abundance and growing complexity. Rapid development in technologies has increased society’s dependence on Information and Communication Technologies (ICT) for routine activities. We use these technologies for interacting with our family and friends, purchasing products, making travel reservations, filing income tax returns, learning, and so on. As individuals conduct these activities, they leave their “digital footprints” or “digital bread crumbs” (Brown, 2011). These “digital footprints” or “digital bread crumbs” capture every detail regarding the user’s interaction with any embedded enterprise-interface system such as time, location, keywords, search results, content created and consumed in the digital environment. These “digital footprints” can be analyzed using analytics to determine patterns and make predictions that can answer questions like: Which course is the most popular? Who are the students not performing well? Despite analytics being common, many questions about them are still unanswered and opportunities exist for improved and refined analytics. Although banks and consumer-oriented retailers have been using sophisticated analytics for quite some time, its potential has barely been tapped in other fields. This chapter describes the current state and future challenges of analytics in one such field, that is, online learning, and commonly known as “learning analytics.”

Ally (2008) defines online learning as “the use of the Internet to access learning materials; to interact with the content, instructor, and other learners; and to obtain support during the learning process, in order to acquire knowledge, to construct personal meaning, and to grow from the learning experience.” Educational institutes have introduced online learning in order to provide a platform for collaborative learning, increased interaction between instructors and students, and elimination of time and place constraints for learning and education. This not only results in improved quality of teaching and learning, but at the same time reduces costs and improves efficiency of educational services.

Learning analytics facilitates better understanding of the learning environment. This approach is profoundly based on the collection, analysis, and interpretation of collected educational data (Bader-Natal & Lotze, 2011). Through sophisticated analytic tools, investigation and visualization of large institutional data sets is improved (Brown, 2011; Buckingham Shum & Ferguson, 2011). Further, learning analytics helps in creating a far more robust and nuanced profile of students and offer deep insights to faculty members (NMC, 2013).

The chapter is structured as follows: Firstly, we present the concept of learning analytics and its difference with “Academic Analytics” and “Educational Data Mining.” Second, we will discuss the process of learning analytics which involves five steps (1) Capture Data, (2) Structure and Aggregate Data, (3) Analyze Data, (4) Representation and visualization, (5) Action, and (6) Refine. Next we will discuss the role of learning analytics in designing and developing various online learning strategies, in designing of course pedagogy, content, course delivery and evaluation. The last section will include challenges of implementing learning analytics and future trends in online education.