Learning analytics dashboards commonly visualize data about students with the aim of helping students and educators understand and make informed decisions about the learning process. To assist with making sense of complex and multidimensional data, many learning analytics systems and dashboards have relied strongly on AI algorithms based on predictive analytics. While predictive models have been successful in many domains, there is an increasing realization of the inadequacies of using predictive models in decision-making tasks that affect individuals without human oversight. In this paper, we employ a suite of state-of-the-art algorithms, from the online analytics processing, data mining, and process mining domains, to present an alternative human-in-the-loop AI method to enable educators to identify, explore, and use appropriate interventions for subpopulations of students with the highest deviation in performance or learning process compared to the rest of the class. We demonstrate an application of our proposed approach in an existing learning analytics dashboard (LAD) and explore the recommended drill-downs in a course with 875 students. The demonstration provides an example of the recommendations from real course data and shows how recommendations can lead the user to interesting insights. Furthermore, we demonstrate how our approach can be employed to develop intelligent LADs.

Learning Analytics Dashboards (LADs) make use of rich and complex data about students and their learning activities to assist educators in understanding and making informed decisions about student learning and the design and improvement of learning processes. With the increase in the volume, velocity, variety and veracity of data on students, manual navigation and sense-making of such multi-dimensional data have become challenging. This paper proposes an analytical approach to assist LAD users with navigating the large set of possible drill-down actions to identify insights about learning behaviours of the sub-cohorts. A distinctive feature of the proposed approach is that it takes a process mining lens to examine and compare students' learning behaviours. The process oriented approach considers the flow and frequency of the sequences of performed learning activities, which is increasingly recognised as essential for understanding and optimising learning. We present results from an application of our approach in an existing LAD using a course with 875 students, with high demographic and educational diversity. We demonstrate the insights the approach enables, exploring how the learning behaviour of an identified sub-cohort differs from the remaining students and how the derived insights can be used by instructors.

No abstract

No abstract

No abstract