Efficiency of Automated Detectors of Learner Engagement and Affect Compared with Traditional Observation Methods

Loading...
Thumbnail Image
Penn collection
Center for Benefit-Cost Studies of Education
Degree type
Discipline
Subject
educational technology
Economics
Educational Assessment, Evaluation, and Research
Education Economics
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Hollands, Fiona
Bakir, Ipek
Contributor
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.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2015-08-01
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection