Research Initiation: Measuring mental demand of interactive textbooks using wearables and web analytics

点击翻译按钮获取中文摘要

Interactive textbooks have created a new web-based form of active learning. Students participating in these multi-sensory, interactive experiences may be learning faster or easier compared to traditional static textbooks. In this project, we will collect data on students' mental demand using non-invasive wearable wristbands as they "read" interactive web-based textbooks called zyBooks. Better understanding of students' mental demand in response to different elements of the textbooks could then inform the design of future instructional materials. The measurement platform developed for this study could also be used outside classroom settings, including study groups and organized events such as Hackathons. Therefore, the proposed research has the potential to significantly advance our understanding about formation of engineers through the acquisition of technical and professional skills and knowledge in both formal and informal settings. Interactive textbooks, such as zyBooks, have been found to have much higher reading rates than traditional textbooks, and their reading rates have also been found to be correlated with course grades. However, it is difficult to ascertain which components of an interactive textbook are driving the increased reading rates. The proposed research targets this problem by providing a platform for continuous measurement of mental demand as students engage with an interactive textbook through reading, watching animations, and interactive problem solving. This project will collect physiological data on students using non-invasive wearable wristbands and synchronize this data with web-based interaction data from zyBooks. The research team will first collect data in a controlled laboratory setting where students will partake in a set of reading and problem solving tasks, and then they will self report their mental demand using the NASA Task Load Index. Using features extracted from the two data streams, the research team will train a machine learning algorithm to predict the student's self-reported mental demand. In phase 2 of the study, the team will collect data on students studying in their natural, everyday study settings and use the trained machine learning algorithm to predict the students' mental demand, which will result in a continuous measurement of students' mental demand as they progress through different animations, activities, and exercises in the zyBook. The measurement platform will provide a first step towards the use of wearables to transform teaching and learning and can be used to explore additional pedagogical questions.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.