Modern personalized learning is being promoted in a manner
analogous to how Internet-based enterprises are modeling
consumers and then recommending additional things to purchase.
A commercial recommendation engine is storing information
on consumers with regard to their demographics
(whatever is legally obtainable, which is a great deal), inferred
interests, as well as their specific purchases. When someone
shows interest in or purchases a specific item, the recommendation
engine then consults the huge repository of consumer analytics
to see what other consumers with similar demographics
and interests in fact purchased and then recommends those
items to the online consumer in real time. The notion in personalized
learning is that similar information can be collected
on learners, including basic demographic information, things
already learned, interests, current learning activities and
assignments. When a learner struggles with a particular task,
the recommendation engine can then consult its learning analytics
repository to see what worked with other learners similarly
situated. In addition, when a learner succeeds with a
particular task, the recommendation engine can then consult
that learner’s profile and see what new learning tasks and
objective are coming up and configure a unit of instruction tailored
to that individual’s interests, prior knowledge, learning
style, and other preferences.