Tools
Tools
Guilcher, Anne (2022) Using artificial intelligence techniques to analyse social media content on COVID-19 children vaccination programs. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (4MB) | Preview |
Preview |
PDF (Configuration manual)
Download (14MB) | Preview |
Abstract
The vaccination of children against the COVID-19 virus was first authorised in the United States in May 2021. Thereafter, people worldwide started to express their personal feelings towards COVID-19 vaccination programs with initiatives aimed specifically at children becoming a hotly debated and highly divisive topic. As information posted on social media platforms such as Twitter is publicly accessible and can be extracted to identify opinions, sentiment, trends and patterns, the purpose of this particular paper is to analyse the variety of opinions specifically linked to COVID-19 vaccination programs amongst children. Classical machine learning models and deep learning algorithms were implemented and correlated to establish the most efficient classifier. 1,019,661 tweets have been gathered, analysed and correlated against key events identified during the rollout of COVID-19 vaccines amongst children as reported by various media outlets. From the analysis undertaken, it has been observed that the majority of the tweets related to COVID-19 vaccination programs of children are neutral, whilst the number of tweets in favour of such programs outnumbers those which expressed negative sentiment. In addition, the findings of this present research have highlighted that the frequency of posts linked to the vaccination of children against COVID-19 follows the timeline and trend of news events. This research paper involved the development and comparison of 12 classifiers with the most optimal model being BERT with an accuracy rate of 90.3%. The proposed approach could similarly be used to monitor existing vaccination programs to help governments better design appropriate communication campaigns and assist them in offering the public clear, detailed and targeted information. In addition, such research findings could support decision makers and health professional to identify and address public safety concerns so as to effectively debunk misinformation and conspiracy theories. Finally, this research initiative could potentially act as a catalyst to help influence public attitudes towards COVID-19 children immunisation programs and increase overall public trust in future vaccination rollouts thereafter.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks 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: | 26 Jan 2023 14:52 |
| Last Modified: | 03 Mar 2023 11:38 |
| URI: | https://norma.ncirl.ie/id/eprint/6130 |
Actions (login required)
 |
View Item |