Engagement Detection with Multi-Task Training in E-Learning Environments

TL;DR

This paper introduces ED-MTT, a multi-task learning system for engagement detection in e-learning, which outperforms existing methods by reducing error and maintaining efficiency.

Contribution

The paper presents a novel multi-task training approach combining mean squared error and triplet loss for engagement detection in online learning environments.

Findings

ED-MTT achieves 6% lower MSE than state-of-the-art methods.

The system is lightweight and has acceptable training time.

It performs well on both public datasets and real-life videos.

Abstract

Recognition of user interaction, in particular engagement detection, became highly crucial for online working and learning environments, especially during the COVID-19 outbreak. Such recognition and detection systems significantly improve the user experience and efficiency by providing valuable feedback. In this paper, we propose a novel Engagement Detection with Multi-Task Training (ED-MTT) system which minimizes mean squared error and triplet loss together to determine the engagement level of students in an e-learning environment. The performance of this system is evaluated and compared against the state-of-the-art on a publicly available dataset as well as videos collected from real-life scenarios. The results show that ED-MTT achieves 6% lower MSE than the best state-of-the-art performance with highly acceptable training time and lightweight feature extraction.