Design Principle of an Automatic Engagement Estimation System in a Synchronous Distance Learning Practice

Abstract

Engagement is an essential component of the learning processes associated with positive learning outcomes. Measuring learner engagement in learning processes is vital to providing insights for enhancing learning activities. Because the learning paradigm has shifted to enable more distance learning practices, machine learning-based automatic engagement estimation methods have been proposed as a new way to measure learner engagement. Nevertheless, most existing methods are built standalone and have yet to be integrated into actual distance learning practice. Furthermore, implementing automatic engagement estimation should ensure technological and ethical impact responsibilities. This article proposes a design principle for the end-to-end integration of automatic engagement in distance learning practice. The MeetmEE system design was introduced to measure learners' emotional engagement in a synchronous distance learning practice. The MeetmEE prototype was deployed in a pilot experiment to evaluate the MeetmEE system design. Finally, the user evaluation results are considered to construct the design principle of ethical implementation. The design principle for implementing the automatic engagement estimation incorporates technical and operational measures.