Learning Fingerprint: Next Generation Intelligent Tutoring System

Open educational systems, like Khan Academy, have become popular by providing education for all. However, with high scalability and ideas on self-directed learning, there is a great risk that student might be left alone in MOOCs.

Learning Fingerprint enables conceptual level recommendations in real-time in order to help student with his/her metacognitive skills and motivation.

The following summary of cumulative consequences of metacognition and Flow are based on author's original studies between 2006 and 2010:

1) Flow can be seen as a background for effective learning. If learner experiences the challenge level to be optimal, he/she is committed to work harder in order to receive the goals. On the other hand, without Flow the learner is more likely to quit the activity.

2) If learner do not know something, she/he can not alone determine why she/he do not know it. This is something all the current LMSs and MOOCs are especially missing. Without personalized view to skills and knowledge, learner can't feel confident. Furthermore, learner needs adaptive recommendations for overriding the difficulties.

3) If learner do not know his/her learning needs, he/she is tend to work with themes already familiar for him/her. Accordingly, learner tend to avoid the real locks of learning.

4) Finally, when left too far behind, a student quits the learning activity.

As a starting point, one critical piece is missing from MOOCs: Without real-time personalized learning, we can not take full advantage on MOOCs and other open educational systems. The student might be left alone.

More results about MOOCs with intelligent tutoring -research will be published during 2014. For more details, contact harri.ketamo@samk.fi.