Deep Learning Based Technique for Covid-19 Vaccination Sentiments Prediction


Authors : Ahmed Mohammed; Dr. A. Pandian

Volume/Issue : Volume 7 - 2022, Issue 6 - June

Google Scholar : https://bit.ly/3IIfn9N

Scribd : https://bit.ly/3PkTJfY

DOI : https://doi.org/10.5281/zenodo.6856347

The COVID-19 pandemic has affected a large number of people, causing great worry, fear, and conflicting feelings or emotions. It has elevated our understanding of the world to unprecedented heights. COVID-19 is rapidly spreading, and the only way to halt it is for the entire population to be vaccinated. However, there is still concern about vaccinations among the general public. From the beginning of vaccinations, many people have refused to have vaccines injected into them. Using survey data acquired via Google form, deep learning techniques were used to build a model for sentiment classification and prediction of COVID-19 vaccination. Public perceptions towards the COVID-19 vaccine were analyzed using natural language processing (NLP) and deep learning techniques. The dataset's responses were 42.60% positive, 35.74% negative, and 21.66% neutral. A convolutional neural network (CNN) and long shortterm memory (LSTM) were used. The LSTM algorithm performed better than the CNN algorithm. The average accuracy scores obtained for CNN and LSTM sentiment classification and prediction models were 68% and 93%, respectively. As evaluation metrics, accuracy, precision, recall, and f-measure were used. This research demonstrates the application of deep learning techniques to sentiment analysis tasks involving the COVID-19 vaccine.

Keywords : Deep Learning, Natural Language Processing, Sentiment Prediction, Covid-19 Vaccination, Convolutional Neural Network, and Long Short-Term Memory.

CALL FOR PAPERS


Paper Submission Last Date
31 - March - 2024

Paper Review Notification
In 1-2 Days

Paper Publishing
In 2-3 Days

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe