A Novel Machine Learning Classification Model to Analyze the COVID-19 Pandemic’s Impact on Academics: Sentiment Analysis Approach

Abstract

AbstractThe COVID-19 Pandemic is considered as the worst situation for human beings; it affected people’s lives worldwide. Due to this pandemic, the respective government authority announced the lockdown to break the coronavirus chain. The lockdown impacted people’s mental health, leading to many psychological issues as well as hampered students’ academics. In this chapter we have studied the impacts on students’ academics due to lockdown effect. The data has been collected via a google form questionnaire circulated to various educational institutes. Further, we have developed a novel machine learning classifier model called Naïve Bayes-Support Vector Machine for analyzing the data, which utilizes the properties of both classifiers by using a deep learning framework. We have used natural language processing (TextBlob, Stanza and Vader) libraries to label the dataset and applied in the proposed NBSVM method and other machine learning models and classified the sentiments into two categories (Positive vs Negative). We also applied the natural language processing libraries used a topic-modelling technique called Latent Dirichlet Allocation to know the essential topics words of both classes from students’ feedback data. The study revealed 83% and 86% accuracy for unigram and bigram, respectively, whereas the precision was 79% and recall 81%. According to NLP libraries’ result, approximately 71% of the feedback’s sentiment is negative, and only 16% of feedbacks are positive. The proposed model shown that (Naïve Bayes-Support Vector Machine) outperforms the other variants of the Naïve Bayes and support vector machine.KeywordsCOVID-19Machine learningNaïve BayesNatural language processingSentiment analysisSupport vector machine