Tools
Tools
-, Dimple (2022) Sentiment Classification of Public Perception regarding Covid-19 Vaccine: Deep Learning and Stacking Ensemble of Machine Learning Approach. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (5MB) | Preview |
Preview |
PDF (Configuration manual)
Download (5MB) | Preview |
Abstract
World Health Organization (WHO) identified Coronavirus as an illness disease, can be named Covid-19. In March 2020, the Covid-19 (define as ‘CO’ stands for Corona, ‘VI’ for the Virus, and ‘D’ for Disease) has been declared a global pandemic that had a significant impact on the economy of the world and a major impact on the lifestyle of people. The entire pharmaceutical industry was focusing on the development of a safe and efficient vaccine. In early December 2020, several vaccinations have been developed and licensed by WHO. Mass production has been started and delivered in several countries. The announcement of a 90 Percent effective rate vaccine raised hope in people, and they have found social media to be a valuable source of sharing their opinions related to vaccines. These perspectives enable researchers to engage in data mining based on public reviews and opinions and provide important insights to help government make better decisions. The purpose of this paper is to examine the evolution of public opinions on the tweets regarding the Covid-19 vaccine on social media like Twitter. For this analysis, the dataset is collected from the Kaggle website. Various libraries of the Natural Language Processing toolkit are used to clean the impurities and noise from data. Cleaned data is not labelled. So, the sentiment analysis approach is used to label the data and categorize it into positive, negative, and neutral sentiments. Text Blob is a python library used to find the polarity and subjectivity score of the labelled dataset. To achieve the objectives, the dataset is split into train and test and then both deep learning models and stack models of machine learning are applied. The results of the models are compared and find that Convolutional Neural Network (CNN) and Long term short memory (LSTM) model has the highest accuracy of 66 Percent to predict the sentiments of the public related to the Covid-19 vaccine on tweets.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RS Pharmacy and materia medica P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > Public Health System |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Tamara Malone |
| Date Deposited: | 24 Jan 2023 12:00 |
| Last Modified: | 03 Mar 2023 12:16 |
| URI: | https://norma.ncirl.ie/id/eprint/6110 |
Actions (login required)
 |
View Item |