Supervised Contrastive Learning for Ordinal Engagement Measurement

TL;DR

This paper introduces a supervised contrastive learning approach for ordinal classification of student engagement levels in virtual learning, addressing class imbalance and order incorporation, with promising results on the DAiSEE dataset.

Contribution

It proposes a novel video-based engagement measurement method using supervised contrastive learning tailored for ordinal classification, incorporating time-series data augmentation techniques.

Findings

Effective classification of engagement levels demonstrated on DAiSEE dataset.

Robust handling of class imbalance and ordinal nature of engagement levels.

Enhanced model training through diverse time-series data augmentation.

Abstract

Student engagement plays a crucial role in the successful delivery of educational programs. Automated engagement measurement helps instructors monitor student participation, identify disengagement, and adapt their teaching strategies to enhance learning outcomes effectively. This paper identifies two key challenges in this problem: class imbalance and incorporating order into engagement levels rather than treating it as mere categories. Then, a novel approach to video-based student engagement measurement in virtual learning environments is proposed that utilizes supervised contrastive learning for ordinal classification of engagement. Various affective and behavioral features are extracted from video samples and utilized to train ordinal classifiers within a supervised contrastive learning framework (with a sequential classifier as the encoder). A key step involves the application of diverse time-series data augmentation techniques to these feature vectors, enhancing model training. The effectiveness of the proposed method was evaluated using a publicly available dataset for engagement measurement, DAiSEE, containing videos of students who participated in virtual learning programs. The results demonstrate the robust ability of the proposed method for the classification of the engagement level. This approach promises a significant contribution to understanding and enhancing student engagement in virtual learning environments.