Measuring Students' Engagement with Digital Interactive Textbooks by Analyzing Clickstream Data

This paper provides an overview of my contributions to a project to measure and predict student's mental workload when using digital interactive textbooks. The current work focuses on analysis of clickstream data from the textbook in search of viewing patterns among students. It was found that students typically fit one of three viewing patterns. These patterns can be used in further research to inform creation of new interactive texts for improved student success. Project Goals The goal of this project is to analyze how students use interactive digital textbooks. To do this, I examine clickstream data from a chemical engineering ZyBook collected across five different semesters. ZyBook is a webbased replacement for textbooks that contains static text passages with interactive animations and practice problems dispersed throughout (ZyBooks). To move through animated content, students are required to click the play button to initiate each step. Students can also click a step number to replay or go back to a previous step. This process generates a clickstream that can be used to determine how long students spend on animations and how their view time changes with animation type, animation length, point in the semester, and other factors. View time is assumed to be an indicator of the effort students spend digesting material. From clickstream data, I hope to discover patterns in students' interaction with ZyBook and use those patterns to inform feature selection for machine learning algorithms in future work. Previous & Related Work Historically, there has been a significant amount of research indicating that students often skip reading assignments in static textbooks. Hobson (2004) suggests that as many as