COVID-19 Ruins Everything: Using a Natural Language Processing System to Capture Disrupted Plans Caused by COVID-19 on Twitter in Japan (Preprint)

Author:

Kamba MasaruORCID,She Wan JouORCID,Ferawati KikiORCID,Wakamiya ShokoORCID,Aramaki EijiORCID

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.

CLINICALTRIAL

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3