Learning analytics is complex

The Indicators project is based on an assumption that learning analytics is data resulting from interactions occurring between agents within a complex adaptive system. This means that charts such as the following that shows the relationship between student clicks within the Moodle learning management system (LMS) and their resulting grade, are not necessarily as useful as they would appear at first glance.

Hits against grade

While there appears to be a nice and neat relationship indicating that the more online students interact within the Moodle environment, the better their grades will be, the reality is vastly more complex. Take the following chart shows the total clicks by the 7582 students who received a pass grade.

Hits for all students receiving a pass grade

This chart shows a range of Moodle clicks (hits) from 0 through to almost 4500 while the average for this group is 271. So while retrospective, aggregated data at the macro level, such as that shown in the first chart is interesting, it does not reveal the seemingly random patterns occurring at the micro levels. Every student is different and so learning analytics based on their behaviors will also be different.


One thought on “Learning analytics is complex”

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s