New Research Article: “Predicting Course Outcomes With Digital Textbook Usage Data”
The article, “Predicting Course Outcomes With Digital Textbook Usage Data” is co-authored by Reynol Junco (Iowa State University and Berkman Center, Harvard University) and Candrianna Clem (University of Texas at Austin) and is is published in Internet and Higher Education.
ISU has posted an overview with comments from Mr. Junco. A full text copy of the article is also available (via the author’s web site) and linked below.
From the Overview Article:
College professors and instructors can learn a lot from the chapters of a digital textbook that they assign students to read. Reynol Junco, an associate professor in Iowa State University’s School of Education, says digital books provide real-time analytics to help faculty assess how students are doing in the class.
Junco and colleague Candrianna Clem collected data from 236 students using e-books in various classes at Texas A&M—San Antonio. On average, students spent nearly 7.5 hours reading over 11 days throughout the 16-week semester. Students who spent more time reading the textbook earned a higher grade in the course, according to the study, published in the journal, Internet and Higher Education.
The findings highlight a value that regular textbooks cannot offer, but adoption of e-books is far from universal in higher education, Junco said. The use of digital books is often driven by student preference, and not everyone is a fan. For the study, 307 students were offered digital textbooks, with the option to print the material, and 236 used the digital version exclusively.
Read the Complete Overview
Direct to Full Text Article (via Co-Author’s Web Site)
Predicting Course Outcomes With Digital Textbook Usage Data (10 pages; PDF)
Internet and Higher Education
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 en- gagement 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).
Note from infoDOCKET: While the focus of this article is on the use of digital textbook analytics to assist in predicting student outcomes we were surprised to not find a discussion or mention of potential privacy concerns with the capture and use of this data.
About Gary Price
Gary Price (firstname.lastname@example.org) is a librarian, writer, consultant, and frequent conference speaker based in the Washington D.C. metro area. He earned his MLIS degree from Wayne State University in Detroit. Price has won several awards including the SLA Innovations in Technology Award and Alumnus of the Year from the Wayne St. University Library and Information Science Program. From 2006-2009 he was Director of Online Information Services at Ask.com. Gary is also the co-founder of infoDJ an innovation research consultancy supporting corporate product and business model teams with just-in-time fact and insight finding.