Implementation of Computational methods to analyze student attentiveness and engagement in Online Learning
Madhura Deshpande & Sharva Gogawale
Department of Industrial Engineering at Tel Aviv University
Via Zoom click here
Abstract:
The online education domain has experienced massive growth in the past few years, especially after the onset of the Covid-19 Pandemic. This transition from on-campus learning to online learning has posed several challenges for educators. In classroom learning, educators are able to read the room and evaluate students’ responses to the material being taught. Visual cues like observing learners’ facial expressions form a feedback mechanism for teachers. Using this feedback, they can modify their teaching pace or content to maintain students’ high engagement levels. However, in virtual classroom environments, it is difficult for teachers to receive this crucial feedback and made adjustments accordingly. In this work, we employ methods like visual computing and deep learning to quantify and gauge learners’ engagement and affective states in the e-learning domain. Further, we implement machine learning techniques to formulate a mathematical model that connects affective state predictions with a comprehensive attentiveness metric. An end-to-end cloud-based system is developed which leverages learners’ live video feed streams to provide detailed attentiveness and engagement analytics to teachers.
Bio:
Sharva Gogawale and Madhura Deshpande are Graduate Researchers in the Industrial Department at Tel Aviv University. Both hold a B.Sc degree in Electrical and Electronic Engineering from Tel Aviv University in the international program.
Advisors: Prof. Irad Ben-Gal and Prof. Parteek Bhatia
Contact: