Twitter talk on COVID-19: a temporal examination of topics, trends and sentiments

Chandrasekaran, Ranganathan, Mehta, Vikalp, Valkunde, Tejali and Moustakas, Evangelos (2020) Twitter talk on COVID-19: a temporal examination of topics, trends and sentiments. Journal of Medical Internet Research, 22 (10) , e22624. ISSN 1438-8871 [Article] (doi:10.2196/22624)

[img]
Preview
PDF - Published version (with publisher's formatting)
Available under License Creative Commons Attribution.

Download (157kB) | Preview
[img] PDF - Final accepted version (with author's formatting)
Restricted to Repository staff and depositor only

Download (2MB)

Abstract

With restricted movements and stay-at-home orders due to COVID-19 pandemic, social media platforms like Twitter have become an outlet for users to express their concerns, opinions and feelings about the pandemic. Individuals, health agencies and governments are using Twitter to communicate about COVID-19. This research builds on the emergent stream of studies to examine COVID-19 related English tweets covering a time period from Jan 1, 2020 to May 9, 2020. We perform a temporal assessment and examine variations in the topics and sentiment-scores to uncover key trends. To examine key themes and topics from COVID-19 related English tweets posted by individuals, and to explore the trends and variations in how the COVID-19 related tweets, key topics and associated sentiments changed over a period of time before and after the disease was declared as pandemic. Combining data from two publicly available COVID-19 tweet datasets with our own search, we compiled a dataset of 13.9 million COVID-19 related English tweets made by individuals. We use Guided latent Dirichlet allocation (LDA) to infer themes and topics underlying the tweets, and use VADER sentiment analysis to compute sentiment scores and examine weekly trends for 17 weeks. Topic modelling yielded 26 topics, grouped into 10 broader themes underlying the COVID-19 tweets. 20.51% of tweets were about COVID-19's impact of economy and markets, followed by spread and growth in cases (15.45%), treatment and recovery (13.14%), impact on healthcare sector (11.40%), and governments' response (11.19%). Average compound sentiment scores were found to be negative throughout the time period of our examination for spread and growth of cases, symptoms, racism, source of the outbreak and political impacts of COVID-19. In contrast, we saw a reversal of sentiments from negative to positive for prevention, impact on economy and market, governments' response, impact on healthcare industry, treatment and recovery. Identification of dominant themes, topics, sentiments and changing trends about COVID-19 pandemic can help governments, healthcare agencies and policy makers to frame appropriate responses to prevent and control the spread of pandemic.

Item Type: Article
Research Areas: A. > Business School > International Management and Innovation
A. > Business School > Marketing, Branding and Tourism
Item ID: 31182
Notes on copyright: ©Ranganathan Chandrasekaran, Vikalp Mehta, Tejali Valkunde, Evangelos Moustakas. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 23.10.2020. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on http://www.jmir.org/, as well as this copyright and license information must be included
Useful Links:
Depositing User: Jisc Publications Router
Date Deposited: 16 Oct 2020 07:48
Last Modified: 10 Jun 2021 02:35
URI: https://eprints.mdx.ac.uk/id/eprint/31182

Actions (login required)

View Item View Item

Statistics

Downloads
Activity Overview
168Downloads
150Hits

Additional statistics are available via IRStats2.