Augmented blended learning by empowering blended teaching with entropy-based learning analytics

The research aims for augmented blended learning by strengthening the blended learning strategy with quantitatively measured learning analytic. This entropy-based learning analytics aims to measure and understand students' progress by quantitively measuring the difference between:

  • the content to be learned,
  • the tutors' expectation of understanding,
  • the student's knowledge.

This quantification will take similar steps taken by Shannon for his information theory using a mathematical formalism to quantitatively measure knowledge (equivalent to Shannon's entropy) and knowledge transfer (equivalent to Shannon's mutual information). Knowledge graphs will represent the content to be learned, the tutors' expectations, and the student's knowledge, as shown in the following figure:

measuring learning rate

Figure 1: Proposed model of measuring learning rate.

Defining an entropy on all three graph representations enables the measurement of the learning progress. This will be done through the (entropy-based) mutual and interaction information. The tutors' expectations use different learning levels as given by, e.g., Bloom's taxonomy (remembering, understanding, applying). Based on these so-called semantic networks, a "speed of learning" will be defined. In addition, AI techniques will also be developed and used to support the creation and use of these semantic networks. This includes the use of Natural Language Processing (NLP) to convert existing courses/knowledge databases to the semantic networks and the introduction of statistical techniques like/extension of ProbLog.

Back to top