Student Engagement in Online Classes During COVID-19: A Sentiment Analysis

Abstract

Especially during the COVID-19 outbreak, online classes helped with flexible and remote learning. However, the effectiveness and participation of students in online classes has yet to be determined. The purpose of this study is to see how students interact with online classrooms and how much they help them learn, focusing on the students’ engagement in online classes. This study highlights the present condition of students' involvement in online classrooms during the COVID-19 pandemic by using Azure Machine Learning for sentiment analysis from qualitative replies. Sentiment analysis is a sort of text mining that identifies and extracts subjective data from source material, allowing users to better understand social sentiment while monitoring online conversations. This method gives a clearer picture of the student's quantitative data and demonstrates a better knowledge of their feelings. The significant findings of this study are: (a) Students' academic effectiveness is not improving. (b) There is a need to restructure the academia according to online circumstances to maintain the students’ engagement. (c) Co-curricular activities have been ignored.