Recommending Insightful Drill-Downs Based on Learning Processes for Learning Analytics Dashboards

Abstract

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.

Intelligent Learning Analytics Dashboards: Automated Drill-Down Recommendations to Support Teacher Data Exploration

“…The work presented in this paper extends our previous works, which have focused on employing AI and process mining techniques to develop intelligent LADs to support instructors with data-driven exploratory analysis of students' learning Shabaninejad, Khosravi, Leemans, et al, 2020;Leemans et al, 2020). Shabaninejad, Khosravi, Indulska, and colleagues (2020) present an approach that can provide instructors with meaningful and efficient ways to gain insight into subsets of students with the highest deviation in an attribute (e.g., performance) compared to the overall class and to recommend subsets of students.…”

“…AID consists of two algorithms that use drill-down trees and a scoring function to search the space across all possible drill-downs to recommend insightful drill-downs. We define the notion of an insightful drill-down as a set of filtering rules that identify a subpopulation of students that deviate from the rest of the class based on performance-and learning process-based metrics, as introduced in Shabaninejad, Khosravi, Indulska, Bakharia, and Isaias (2020) and Shabaninejad, Khosravi, Leemans, Sadiq, and Indulska (2020). For performance-based divergence, the Kullback-Leibler (KL) divergence function (Kullback & Leibler, 1951) is used.…”

The Virtual Tutor: Combining Conversational Agents with Learning Analytics to support Formative Assessment in Online Collaborative Learning

“…There are different approaches for LA data analysis. For instance online analytical processing (OLAP) and dashboards have been implemented [30,35,44] in the context of LA. However, both struggle with acceptance.…”

Reviewing Process Mining Applications and Techniques in Education

“…They used a combination of methods (data from more than one source, process and sequence mining) to gain an in-depth understanding of the programming learning. Shabaninejad, et al [42] used LAD as source of rich and complex data about students and their learning activities. The learning processes of students were visualized and compared giving insights to educators that could be used to adjust educational process.…”