 Social media-based social–psychological community resilience analysis of five countries on COVID-19Jaber Valinejad (),
Zhen Guo,
Jin-Hee Cho and
Ing-Ray Chen
Journal of Computational Social Science, 2023, vol. 6, issue 2, No 21, 1032 pages Abstract: Abstract Community resilience (CR) has been studied as an indicator to measure how well a given community copes with and recovers from a given disaster. Social–psychological community resilience (SPCR) has been used as a basis to determine public policy directions based on priority. Although the impact of the COVID-19 has been serious all over the world and interferes every aspect of our daily life, some countries have handled this disaster better than others due to their different disaster management policies and perceptions about the disaster. In this work, we are interested in measuring and analyzing SPCR through social media information in five different countries which can reflect different disaster management policies and perceptions toward the COVID-19. In the literature, measuring SPCR has been discussed, but the key attributes have not been agreed upon. We propose to use two attributes for measuring SPCR, i.e., community wellbeing (CW) and community capital (CC), because social and psychological resilience can be the firm basis for a community to be restored and reinvented into the so-called transformative community to ensure sustainability in the future generation. We use Tweeter data and investigate how each country shows different trends of SPCR in response to real and fake tweets generated during a COVID-19 period using machine learning and text-mining tools. We employ tweets generated in Australia (AUS), Singapore (SG), Republic of Korea (ROK), the United Kingdom (UK), and the United States (US), during March–November 2020 and measure the SPCR of each country and its associated attributes for analyzing the overall trends. Our results show that ROK among the five countries in our study has the highest level in CW, CC, and the resulting SPCR on real tweets reflecting reality, a result that matches well with the fact that ROK is resilient to COVID-19 during March–November 2020. Further, our results indicate that SPCR on real tweets is up to 80% higher than SPCR on fake tweets, suggesting that a much stronger community resilience may be achieved on real tweets. Finally, our results show that there is a negative correlation between SPCR values on fake and real tweets overall when considering all the tweets of the five countries to derive the overall trends. However, for each country, we observe a different correlation, either positive or negative, depending on each country. This implies that there should be further investigation of analyzing SPCR by considering unique cultural and national characteristics of each country. Keywords: Applied computing; Psychology; Computing methodologies; Model verification and validation; Social–psychological community resilience; Social media; Fake news; Real news; COVID-19; Text mining; Data science; NLP (Natural language programming) (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:6:y:2023:i:2:d:10.1007_s42001-023-00220-z Ordering information: This journal article can be ordered from DOI: 10.1007/s42001-023-00220-z Access Statistics for this article Journal of Computational Social Science is currently edited by Takashi Kamihigashi More articles in Journal of Computational Social Science from Springer |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.