Predicting course outcomes with digital textbook usage data

Abstract

Digital textbook analytics are a new method of collecting student-generated data in order to build predictive models of student success. Previous research using self-report or laboratory measures of reading show that engagement with the textbook was related to student learning outcomes. We hypothesized that an engagement index based on digital textbook usage data would predict student course grades. Linear regression analyses were conducted using data from 233 students to determine whether digital textbook usage metrics predicted final course grades. A calculated linear index of textbook usage metrics was significantly predictive of final course grades and was a stronger predictor of course outcomes than previous academic achievement. However, time spent reading, one of the variables that make up the index was more strongly predictive of course outcomes. Additionally, students who were in the top 10th percentile in number of highlights had significantly higher course grades than those in the lower 90th percentile. These findings suggest that digital textbook analytics are an effective early warning system to identify students at risk of academic failure. These data can be collected unobtrusively and automatically and provide stronger prediction of outcomes than prior academic achievement (which to this point has been the single strongest predictor of student success).