ABSTRACT
The COVID-19 pandemic has essentially transformed the way millions of people across the world live their life. As offices remained closed for months, employees expressed conflicting sentiments on the work from home culture. People worldwide now use social media platforms such as Twitter to talk about their daily lives. This study aims to gage the public’s sentiment on working from home/remote locations during the COVID-19 pandemic by tracking their opinions on Twitter. It is essential to study these trends at this point in the pandemic as organizations should decide whether to continue remote work indefinitely or reopen offices and workspaces, depending on productivity, and employee satisfaction. Tweets posted in the live Twitter timeline is used to generate the set of data and accessed through Tweepy API. About 2 lakh tweets relevant to the remote work during the pandemic were tokenized and then passed to Naive Bayes classifier that classifies the sentiments positive, negative, neutral to every tweet. Our findings emphasize on population sentiment which is the effects of the COVID-19 pandemic, especially resulting from the work from home policy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
The COVID-19 pandemic has essentially transformed the way of leading a life for millions of people across the world. As offices remained closed for months, employees expressed conflicting sentimental analysis on the workfrom-home culture. People worldwide use social media platforms such as Twitter to talk about their daily lives madea trend in the online platform. This research study aims to gauge the public's sentiment on working from home/ remotelocations during the COVID-19 pandemic by tracking their opinions on Twitter. The existing random forest modeltrained the data faster but failed to predict the results faster. Therefore, an ensemble model is proposed to predict anoutcome using a distinct modeling algorithm. An ensemble classifier has been used for enhancing the performancesusing the base learning classifiers such as Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM),Logistic Regression (LR) form an Ensemble classifier. The proposed ensemble model aggregates each base model forthe prediction and results for the unseen data. These tokens are then passed to the Ensemble classifier that classifiesthe sentiments and assigns a polarity (positive, negative, neutral) to every tweet. The proposed Ensemble methodimprove the average prediction performance over any contributing member in the ensemble. The results obtained bythe proposed Ensemble model reached accuracy of 97.47 % when compared to the existing models such as DeepLSTM, SVM model that obtained accuracy of 83 %, 84.46 % © 2022,International Journal of Intelligent Engineering and Systems. All Rights Reserved.