Jisc Learning Analytics: Major applications of learning analytics

Learning analytics is about far more than
just identifying students that are at risk of failure or withdrawal. We’ve identified four different uses of learning
analytics that occur throughout the world in educational institutions. The first major application of learning analytics
that we see and that which has grabbed the attention of the educational media and of
senior management at educational institutions is early alert systems or student success
systems, as they’re sometimes known. What these do is they take historical data
about previous cohorts of students and develop a predictive model which then the data of
an individual student could be mapped against. And that shows then how likely they are to
have problems academically or to drop out. It also produces what is known as actionable
intelligence and you can then take an intervention on the basis of that intelligence, which might
be contacting the student for example or giving the student some kind of feedback in order
to try and improve their chances of academic success. The next major use of learning analytics that
we’ve encountered is course recommender systems. Now you may be used to buying a book on Amazon
or selecting a film on Netflix and those may be because you’ve been recommended a particular
item by those systems. That might be based on your past choices or
it may be based on the choices of people like you. Course recommender systems work in a similar
way. So students are often faced with a bewildering
choice of courses to select and these systems look at your past academic history, and perhaps
your career aspirations, and then recommend the next course for you to take based on how
likely you are to succeed in that course. The third major area of learning analytics
that we’ve encountered is adaptive learning. Now again, this tries to move beyond the one-size-fits-all
approach to learning and provide personalised content to learners. Publishers have seized on this and are now
adapting their textbooks; enhancing them through a more personalised experienced to the students. As they progress through that content depending
on how they’ve done they will have different content presented to them. It doesn’t have to just be about that kind
of model though. We could do far more innovative things with
adaptive learning. And people have already started experimenting
with pairing you up with other students, for example, that are encountering the same issue
or perhaps pairing you up with a more expert student that’s prepared to offer you their
expertise. We’re only at the beginning of this whole
movement to adaptive learning and I think as part of a more rounded educational experience
there are huge potentials here. The fourth major use of learning analytics
is curriculum design, so looking at the curriculum, looking at the data that we’ve got about it,
and seeing whether it’s functioning as we intended it to. Are students accessing the forums and contributing
to those? Are they looking at particular bits of learning
content? Are they participating in the learning as
we intended them to? We have unprecedented opportunities to analyse
that process and then to make evidence-based changes to the curriculum either on the fly,
as the students are progressing through the course, or subsequently for further cohorts
of students that take your modules in the future. So we started off looking at the biggest use
of learning analytics, which is identifying students at risk and we’ve looked at several
other applications that are emerging. I think we can expect a lot of new uses of
data about students to be emerging over the next few years and we’re really only at the
start of a very interesting journey here.

Leave a Reply

Your email address will not be published. Required fields are marked *