id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-028394-oq4z0nhc	Al-Doulat, Ahmad	Making Sense of Student Success and Risk Through Unsupervised Machine Learning and Interactive Storytelling	2020-06-09		.txt	text/plain	4267	250	52	We report on the design and evaluation of FIRST, Finding Interesting stoRies about STudents, that provides an interactive experience in which the advisor can: select relevant student features to be included in a temporal model, interact with a visualization of unsupervised learning that present patterns of student behavior and their correlation with performance, and to view automatically generated stories about individual students based on student data in the temporal model. Our approach to interactive sensemaking has three main parts: (1) a temporal student data model, (2) data analytics based on unsupervised learning, and (3) storytelling about the student experience. Most of the learning management tools involve data scientists in the knowledge discovery process to design the student data model, analytics approach, visualizations, and a reporting system to understand students' patterns of success or failure. FIRST automatically generates stories for each student using the features selected in the temporal data model.	./cache/cord-028394-oq4z0nhc.txt	./txt/cord-028394-oq4z0nhc.txt