Student’s engagement detection based on computer vision: A Systematic Literature Review

Student engagement detection is receiving increasing attention due to its crucial role in influencing academic performance and learning outcomes. As learning environments increasingly shift toward online and hybrid modes, understanding and monitoring student engagement through automated means has become an essential focus in educational technology. Computer vision techniques offer promising capabilities for detecting and interpreting student behaviors indicative of engagement. This paper presents a systematic literature review (SLR) on engagement detection in learning environments using computer vision methods. The objective of this study is to examine and categorize the types of student engagement detected, the learning contexts in which detection occurs, and the methods employed for such detection. Specifically, we analyze the types of data sources, datasets, and features used, as well as the preprocessing and feature engineering techniques applied to enhance model accuracy. Furthermore, we investigate the types of machine learning/Deep learning models adopted and how their performance is evaluated. Based on the findings from selected studies, this review aims to identify key contributions, existing challenges, and potential directions for future research in the domain of automated student engagement detection.