ABSTRACT
One theme that emerges in several of the conversations with experts in learning analytics is that the data being used for learning analytics is not ideal in its current format: it is largely derived from logging systems, initially designed for tracking bugs in software and monitoring server performance rather than for understanding educational processes. Dragan Gasevic suggests that people need to collect data that is measuring aspects of learning, helping them, for example, to understand levels of understanding, metacognition and the affective states of students. Whatever the underlying data sources, there is much that can be done to enhance the analytics taking place on the data. John is carrying out cluster analysis, developing different 'student types', based on how they interact. He intends to use these categories to refine the algorithms, predictions and inferences that can be drawn from student behaviour.
