Document Type
Working Paper
Date of this Version
8-2015
Abstract
This report investigates the costs of developing automated detectors of student affect and engagement and applying them at scale to the log files of students using educational software. We compare these costs and the accuracy of the computer-based observations with those of more traditional observation methods for detecting student engagement and affect. We discuss the potential for automated detectors to contribute to the development of adaptive and responsive educational software.
Keywords
educational technology
Included in
Economics Commons, Educational Assessment, Evaluation, and Research Commons, Education Economics Commons
Date Posted: 11 January 2022