Olasoji Amujo
COVID-19 in the UK: sentiment and emotion analysis of Tweets over time.
Amujo, Olasoji; Ibeke, Ebuka; Iwendi, Celestine; Boulouard, Zakaria
Authors
Contributors
Celestine Iwendi
Editor
Zakaria Boulouard
Editor
Natalia Kryvinska
Editor
Abstract
We performed an analysis of tweets concerning the COVID-19 pandemic in the UK over a two-year period, selecting fifteen timelines. Over 110,000 tweets were obtained from Twitter and analysed using BERT and Text2Emotions for sentiment and emotion analysis, respectively. The most common emotions expressed on Twitter about COVID-19 in the UK appeared to be surprise and fear. This is not unusual, given the unprecedented nature of the pandemic. However, as time passed, there was a notable shift in sentiment towards other emotions, such as sadness and happiness. Moreover, more positive than negative sentiments were observed over the fifteen timelines studied: eight positive sentiments to seven negative ones. Further, results indicated that confirmed cases, deaths, and government policy heavily influenced public sentiment. This study sheds light on the collective state of mind surrounding the pandemic and provides insight into how people reacted emotionally over time to COVID-19. The results provide valuable insights for policymakers and other stakeholders looking to understand how people respond in times of crisis. Furthermore, it illustrates how sentiment analysis can be used effectively to gain deeper insights into public perception over time. As such, this study is a valuable contribution to understanding the human emotional response, demonstrating how sentiment and emotion can be used to better comprehend a situation and react accordingly.
Citation
AMUJO, O., IBEKE, E., IWENDI, C. and BOULOUARD, Z. 2023. COVID-19 in the UK: sentiment and emotion analysis of Tweets over time. In Iwendi, C., Boulouard, Z. and Kryvinska, N. (eds.) Proceedings of the 2023 International conference on advances in communication technology and computer engineering (ICACTE'23): new artificial intelligence and the Internet of things based perspective and solutions, 23-24 February 2023, Bolton UK. Lecture notes in networks and systems, 735. Cham: Springer [online], pages 519-535. Available from: https://doi.org/10.1007/978-3-031-37164-6_38
Conference Name | 2023 International conference on advances in communication technology and computer engineering (ICACTCE'23); new artificial intelligence and the Internet of things based perspective and solutions |
---|---|
Conference Location | Bolton, UK |
Start Date | Feb 24, 2023 |
End Date | Feb 24, 2023 |
Acceptance Date | Feb 9, 2023 |
Online Publication Date | Sep 24, 2023 |
Publication Date | Dec 31, 2023 |
Deposit Date | Feb 16, 2023 |
Publicly Available Date | Sep 25, 2024 |
Publisher | Springer |
Pages | 519-535 |
Series Title | Lecture notes in networks and systems |
Series Number | 735 |
Series ISSN | 2367-3370; 2367-3389 |
Book Title | Proceedings of the 2023 International conference on advances in communication technology and computer engineering (ICACTCE'23); new artificial intelligence and the Internet of things based perspective and solutions, 23-24 February 2023, Bolton, UK |
ISBN | 9783031371639 |
DOI | https://doi.org/10.1007/978-3-031-37164-6_38 |
Keywords | COVID-19; Sentiment analysis; Emotion analysis; Text2Emotion; BERT model |
Public URL | https://rgu-repository.worktribe.com/output/1887998 |
Files
This file is under embargo until Sep 25, 2024 due to copyright reasons.
Contact publications@rgu.ac.uk to request a copy for personal use.
You might also like
Tourism cloud management system: the impact of smart tourism.
(2022)
Journal Article
Covid-19 fake news sentiment analysis.
(2022)
Journal Article
Artificial intelligence (AI) for productivity: big data and AI in agriculture.
(2022)
Presentation / Conference
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search