What is Learning Analytics?

Our research department is currently housing a student from a different institution who is interested in mobile learning. She has just finished her doctorate in a Spanish university and is about to head home to China. During a welcome meeting our guest proclaimed an interested in mobile learning and Learning Qnalytics. One of our departments professors then singled me out, “David knows all about Learning Analytics”.

I really should know about Learning Analytics. I’m currently involved in a EU project with the term Learning Analytics in the title. I helped write a paper on tools for learning analytics and have read many papers coming out of our department on it.

The student looked at me, raised an eyebrow. I waved my hand, said that we can catch up later, worried that I still don’t haven’t a clue about Learning Analytics. I just don’t have an answer to the question: ‘what is Learning Analytics?’. I can’t claim that data informed decision-making is a new thing, I don’t suppose it’s even new in the context of applying it to education. Also, how does it differ to educational data mining? I’ve never really understood that; I read somewhere that education data mining included academic analytics in it’s scope, I guess because academics aren’t learning anything they can’t be included in learning analytics, who knows.

The trouble is that when it comes to Learning Analytics I don’t think there is a good snappy sound bite on learning analytics to spurt out when your professor drops you in it at the meeting. Fortunately there a list of 5 things in a Cetis briefing paper by my colleagues that I always return too whenever I am lost in learning analytics. These 5 areas of learning analytics are

Topic Models to explore and compare communities

Recently I’ve been playing with an R wrapper for a machine language library called Mallet  to generate lists of topics from a series of text documents. The technique is called Topic Modelling and I have gotten to grips with it from Ben Marwick‘s readings of archaeology papers which has some excellent reusable code.  A topic in my model is simply a collection of words that make up the topic. Mallet can do all sorts of fancy things with the words and topics, it can tell me how likely a word is to appear in the topic, analyse text and tell me how much of that text belongs to which topics.