USAGE OF LEARNING ANALYTICS TO IMPROVE INDIVIDUAL KNOWLEDGE NUGGETS DELIVERY

C. Ploder , R. Bernsteiner , T. Dilger 

Management Center Innsbruck (AUSTRIA)
Every student of our current Bachelor and Master programs experiences in his or her cohort the same set of learning routines and knowledge transfer/sharing methods by our courses. Therefore, the authors have done a lot of research in the past on how an individual knowledge delivery based on knowledge nuggets can be set up to better support the different students' needs. They have different backgrounds, ages, preferences, learning styles, and levels of expertise in various topics. Knowledge Nuggets are considered learning materials organized within small, defined topics. This granularity makes the content easier to consume at an individual pace. Depending on their scope and size, these nuggets can vary. Also, each nugget can be presented on different cognitive levels. The level does not indicate the amount of content or the shared knowledge's difficulty but how the learning is prepared and conveyed. However, all three levels offer the same characteristics: practicality, reproducibility, and manageable time. These characteristics are of great relevance to be accepted as training methods in any educational program. The progressive redistribution of dimensions occurs in elaboration, learning technology, and the cognitive load.

Exactly here, learning analytics is of interest for an individualized part of the delivered knowledge. Learning analytics is widely regarded as a critical enabler for the future of learning. There is no consensus on a single definition of the term. Eric Duval gives an approach that illustrates very clearly how learning analytics can be seen: "Learning analytics is about collecting the traces that learners leave … and improving learning based on those traces." But a crucial aspect in the practical integration is privacy, or the right to control what others know about you as a student or teacher in the system. An alternative way to deal with privacy issues is to give students control over their data. This approach ends in a possible implementation following the principles of Privacy by Design.

Transferring knowledge with the knowledge nuggets and afterward measuring the outcome and the student's stress level will help predict or analyze the individual student's behavior and enables a more precise prediction of which type can be best for future knowledge. All of this has to be set up based on theories and integrated into our newly designed learning environment. The paper will show a best practice implementation framework for improving a student's outcome in correlation with the stress that exists to increase our bachelor and master students' overall knowledge gain based on learning analytics.