Getting started with learning analytics

I suspect that most of us tip-toe around the edge of learning analytics: we are aware of its existence, have a cursory understanding of what it is and does, but maintain a distance as we are a little suspicious of it. Well, if you feel that it’s time to jump right in and develop an in-depth understanding of learning analytics, then here’s the best way to get started.

Looking at the list of editors of the new freely available online book, Handbook of Learning Analytics, you’ll reassuringly see the name George Siemens, a heavyweight by anyone’s standards. He and his three fellow editors (Charles Lang, Alyssa Wise and Dragan Gašević) have assembled impressive publication, “designed to meet the needs of a new and growing field. It aims to balance rigor, quality, open access and breadth of appeal and was devised to be an introduction to the current state of research.” Published by the Society for Learning Analytics Research (SOLAR), the book is titled as ‘First edition’, heralding what will hopefully be a series as the field evolves over the next decade or so.

This edition of about 350 pages is divided into four sections: Foundations, Techniques, Applications and Systems. So there’s something here for everyone, from newby to expert, and you can download single chapters if you don’t require the whole book. If you start at the beginning, (Chapter 1: ‘Theory and Learning Analytics’), you’ll reassuringly find (for me, anyway) that it’s written by a couple of Australians from the University of Technology Sydney, Simon Knight and Simon Buckinham Shum.

Somewhat to my surprise, and I could be wrong, but I’ve been unable to find a definition of learning analytics in the book. Checking the SOLAR website, I couldn’t find one there either. Perhaps it’s meant to be self-evident. Its meaning is certainly implied in ‘The Challenge’ faced by SOLAR:

We are experiencing an unprecedented explosion in the quantity and quality of information available not only to us, but about us. We must adapt individually, institutionally and culturally to the transition in technologies and social norms that makes this possible, and question their impacts. What are the implications of such data availability for learning and knowledge building — not only in established contexts such as institutional learning platforms, but also in the emerging landscape of free, open, social learning online?

For myself and what learning analytics means, it takes me back to the very beginnings of my teaching career, when I was given the unenviable task of improving the mathematical ability of a group of students at Hobart Technical College who had scored between 0 and 20 per cent on their mid-year examination. Faced with this challenge, I asked to see their exam papers, so that I could try to see what their difficulties were. I was trying to use the data provided in the papers to analyse what they lacked in knowledge so that I could help them remedy this deficiency. In other words, I was applying learning analytics to help my teaching.

Step forward four decades from my primitive application, and where are we? Well, peruse the chapter titles and find whatever most appeals (there’s even one on ethics): my curiosity was raised by Chapter 10: ‘Emotional Learning Analytics’.

The aim here seems to be to provide the learner with an “Affective AutoTutor: an intelligent tutoring system (ITS) with conversational dialogs that automatically detects and responds to learners’ boredom, confusion, and frustration.” In other words, the online automatic tutor is able to ascertain your emotional state and respond appropriately.

How on earth can it do this?! One way is simply by the expression on your face, judged by analysis of your visage on your webcam. Does this pic reveal the student’s emotional state? Edgy stuff indeed. As the author Sidney D’Mello explains concerning the figure, “Automatic tracking of facial features using the Computer Expression Recognition Toolbox. The graphs on the right show likelihoods of activation of various facial features (e.g., brow lowered, eyelids tight- ening).”

I hope I’ve given you enough of a taster to inspire you to take a measured look and appraisal of learning analytics. It’s not going away, so you’d better raise your awareness and knowledge level of this ever-growing enterprise.