Assessing Participants Engagement in Virtual Meetings by Using Facial Landmarks and Deep Learning

This article explores the integration of facial landmarks and deep learning techniques for emotion recognition to enhance user engagement and communication quality in virtual meetings. With the increasing prevalence of virtual communication assessing participants engagement remains a critical challenge. Through the development of Deep Neural Network, Convolutional Neural Network, and hybrid CNN combined with Recurrent Neural Network models, by adapting these architectures to suit the specific requirements of engagement assessment, this study investigates the effectiveness of these algorithms in assessing engagement levels during virtual meetings. this study also contributes to the ongoing development of robust and reliable automated systems capable of accurately assessing engagement in virtual meeting environments, with implications for remote education and work settings.