Accepted for/Published in: JMIR Infodemiology
Date Submitted: Jun 6, 2023
Open Peer Review Period: Dec 18, 2023 - Feb 12, 2024
Date Accepted: Mar 6, 2024
(closed for review but you can still tweet)
COVID-19 Ruins Everything: Using a Natural Language Processing System to Capture Disrupted Plans Caused by COVID-19 on Twitter in Japan
ABSTRACT
Background:
Even though COVID-19 is a pandemic, its impact is not only limited to public health but has spanned across economy, education, work style or social relationships. As the COVID-19 studies proliferating in the past two years, whether the studies would yield insights that are relevant to the individuals in the society becomes important.
Objective:
This study focuses on uncovering and tracking the concerns in Japan across the COVID-19 period by investigating Japanese individuals' self-disclosing of life plan disruption on the social media, hence, yielding field evidence of which concerns might warrant further addressing for individuals living in Japan.
Methods:
We have extracted 300,778 tweets using "Corona no-sei (due to COVID-19, because of COVID-19, or considering COVID-19) as a query phrase, which allowed us to identify the activities and life plans disrupted due to COVID-19. The number of tweets compares with the number of COVID-19 cases to analyze the correlation. In addition, we analyze frequent co-occurrence words.
Results:
Our findings showed that while education surfaced as the top concern when Japanese government announced the first state of emergency. We also observed a sudden surge of anxiety about shortage of materials such as toilet paper. While these concerns were relatively short-term concerns, as the pandemic dragged further and more state of emergencies being announced, more concerns about long-term life plans such as career, social relationships, and education started showing.
Conclusions:
Overall, by adding the analysis on "Corona no-sei" to the conventional symptom-based monitoring, we were able to identify the underlying concerns at the peak of the disruption and across the whole time span of the three announcements of state of emergency.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.