Examples of LA at #LAK12

The examples that were introduced this week are very inspiring - not only the actual application, but also the general approach and concerns. I would advice everybody to watch the whole conversation between George Simons and Vernon Smith at Educause 2011, not only the part by Vernon. George gives some very good concerns at the end of his talk. Just to mention one: "Analytics must be rooted in learning sciences".

I liked the Rio Pace example very much because they were able to create effective predictions using straightforward data and only a naive bayesian classifier. This is quite opposite to practice in educational research: Naive bayes is not a solid model, statistically, but it works fine in practice.

The Signals project at Purdue is quite interesting. We apply something similar in our portfolio system (called epass) for some of the schools, but we are not specificaly looking at retention rates.

This week I have played around with the free datamining tool Rapidminer using some of the usage data of our epass system for medical trainees (1.8 million data points over two years). I discovered a very clear picture of how the portfolio is used during the day: lunch break, dinner, small peak after dinner... But also that users spent more time using the portfolio when they log on in the weekend. It is only a start, but it is a nice way of getting into the tool.

Being a data scientist - a revival?

After watching the presentation of John Rauser (Amazon) at Strata New York 2011 on the topic of data scientist carreer, I came to the amazing conclusion that I am trained (amongst other things) as a data scientist!  I have a background in mathematics (bachelor at Nijmegen), but also in operations research and artificial intelligence (master at Maastricht). The program in Maastricht is called "Knowledge Engineering" - but maybe they should switch their name to "Data Science" to keep at track with this new hype...   I have been a teacher in computer science at that program for almost 10 years, but currently I have a position at the educational department of our faculty and am mainly involved in implementing clever computer applications to help learning. This course in learning analytics (#LAK12) might bring the data scientist in me back to life.

By the way, I agree  completely with John Rauser that writing skills, being sceptical and curiosity are vital traits - but that is true for all scientists.

Using Wolfram Alpha

Inspired by one of the big data video's in the first week of our #LAK12 mooc, I decided to look at Wolfram Alpha again. Since I used my iPad to view the video, I used the tablet to visit the website. It adviced me to install the app, which is not for free. I decided to do so and started playing around. The presenter argued that Wolfram only uses validated cured data and that harvesting the web is not a good idea. I only agree if you do not ask any question to Wolfram Alpha that any child wouldn't know. For instance, they have a database for composers. JS Bach is in it, but Louis Couperin is not. Why? It knows about food, but it only knows one type of cheese, probably the US type. In opinion this is typical behavior of mathematicians: reduce reality to something you can compute - then take the answer for more true than the real thing. It is a nice tool for engineers, but "star trek" is still very far away. Let's stick to Wikipedia for a while!

Starting with my first MOOC #LAK12

My name is Jeroen Donkers.  I am assistant professor at the department of educational development and research of the faculty of health, medicine and life sciences of Maastricht University in the Netherlands. My interest is the application of computers to improve learning - in a very broad sense. I am trained in Knowledge Engineering (applied mathematics and computer science) and wrote my PhD thesis on artificial intelligence.

I created this blog because I participate in the MOOC (Massive open online course) on learner analytics: LAK 2012. (see lak12.mooc.ca). The course will continue for the next 8 weeks. I will try to add an entry every week.

My reason for participating in the course that I am interested in applying learning analytics in the near future. In particular, we want to know what the relation is between the use of our feedbacksystem ProF and the test-outcomes of our students.   Next week I will submit a final version of a project proposal to the Learner Analytic tender of SURF - more on this in a next blog.