id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-028437-lza8eo9n	Shabaninejad, Shiva	Recommending Insightful Drill-Downs Based on Learning Processes for Learning Analytics Dashboards	2020-06-09		.txt	text/plain	4496	237	54	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. 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. In our approach, the notion of an insightful drill-down is defined as a set of filtering rules that identify a sub-cohort of students whose learning processes are most differentiated from the rest of the students. LP-AID employs a process mining method called Earth Movers' Stochastic Conformance Checking (EMSC) [29] to compute the distance between learning processes of different cohorts to recommend insightful drill-downs. Specifically, we apply LP-AID to data from a course with 875 students, with high demographic and educational diversity, to demonstrate the drill-down recommendations and to explore the possible insights that can be derived from them.	./cache/cord-028437-lza8eo9n.txt	./txt/cord-028437-lza8eo9n.txt