tetano
Editor, Senior Moderator
J Med Internet Res. 2020 Apr 16. doi: 10.2196/19118. [Epub ahead of print]
Health Communication Through News Media During the Early Stage of the COVID-19 Outbreak in China: A Digital Topic Modeling Approach.
Liu Q[SUP]1,[/SUP][SUP]2[/SUP], Zheng Z[SUP]3,[/SUP][SUP]4[/SUP], Zheng J[SUP]3,[/SUP][SUP]4[/SUP], Chen Q[SUP]1[/SUP], Liu G[SUP]5[/SUP], Chen S[SUP]6[/SUP], Chu B[SUP]6[/SUP], Zhu H[SUP]6[/SUP], Akinwunmi B[SUP]7,[/SUP][SUP]8[/SUP], Huang J[SUP]9[/SUP], Zhang CJP[SUP]10[/SUP], Ming WK[SUP]3[/SUP].
Author information
Abstract
BACKGROUND:
In December 2019, a few COVID-19 cases were first reported in Wuhan, Hubei, China. Soon after, increasing cases were detected in other parts of China and soon the disease broke out in China. As this dreadful disease spreads rapidly, the mass media has been active in community education on COVID-19 by delivering health information about this novel coronavirus, such as its pathogenesis, spread, and prevention/containment.
OBJECTIVE:
This study collected media reports on COVID-19 and investigated the patterns of media-directed health communications as well as the role of media in this ongoing COVID-19 crisis in China.
METHODS:
We adopted the WiseSearch database to extract related news articles about coronavirus from major press media, between January 1st, 2020, to February 20th, 2020. We then sorted and analyzed the data using Python software and Python package Jieba. We sought a suitable topic number with evidence of the coherence number. We operated Latent Dirichlet Allocation (LDA) topic modeling with the suitable topic number and generated corresponding keywords and topic names. We then divided these topics into different themes by plotting them into two-dimensional plane via multidimensional scaling.
RESULTS:
After removing duplications and irrelevant reports, our search identified 7791 relevant news reports. We listed the number of articles published per day. According to the coherence value, we chose 20 as our number of topics, and the generated topics' themes and keywords. These topics were categorized into nine main primary themes based on the topic visualization figure. The top three popular themes were prevention and control procedures, medical treatment and research, global/local social/economic influences, accounting for 32.6%, 16.6%, 11.8% of the collected reports respectively.
CONCLUSIONS:
Topic modeling of news articles can produce useful information about the significance of mass media for early health communication. Comparing the number of articles each day and the outbreak development, we note that mass media news reports in China lag behind the development of COVID-19. The major themes accounted for around half the content and tended to focus on the larger society than on individuals. The COVID-19 crisis has become a global issue, and society has also become concerned about donation and support as well as mental health. We recommend that future work should address the mass media's actual impact on readers during the COVID-19 crisis through sentiment analysis of news data.
PMID:32302966DOI:10.2196/19118
Health Communication Through News Media During the Early Stage of the COVID-19 Outbreak in China: A Digital Topic Modeling Approach.
Liu Q[SUP]1,[/SUP][SUP]2[/SUP], Zheng Z[SUP]3,[/SUP][SUP]4[/SUP], Zheng J[SUP]3,[/SUP][SUP]4[/SUP], Chen Q[SUP]1[/SUP], Liu G[SUP]5[/SUP], Chen S[SUP]6[/SUP], Chu B[SUP]6[/SUP], Zhu H[SUP]6[/SUP], Akinwunmi B[SUP]7,[/SUP][SUP]8[/SUP], Huang J[SUP]9[/SUP], Zhang CJP[SUP]10[/SUP], Ming WK[SUP]3[/SUP].
Author information
Abstract
BACKGROUND:
In December 2019, a few COVID-19 cases were first reported in Wuhan, Hubei, China. Soon after, increasing cases were detected in other parts of China and soon the disease broke out in China. As this dreadful disease spreads rapidly, the mass media has been active in community education on COVID-19 by delivering health information about this novel coronavirus, such as its pathogenesis, spread, and prevention/containment.
OBJECTIVE:
This study collected media reports on COVID-19 and investigated the patterns of media-directed health communications as well as the role of media in this ongoing COVID-19 crisis in China.
METHODS:
We adopted the WiseSearch database to extract related news articles about coronavirus from major press media, between January 1st, 2020, to February 20th, 2020. We then sorted and analyzed the data using Python software and Python package Jieba. We sought a suitable topic number with evidence of the coherence number. We operated Latent Dirichlet Allocation (LDA) topic modeling with the suitable topic number and generated corresponding keywords and topic names. We then divided these topics into different themes by plotting them into two-dimensional plane via multidimensional scaling.
RESULTS:
After removing duplications and irrelevant reports, our search identified 7791 relevant news reports. We listed the number of articles published per day. According to the coherence value, we chose 20 as our number of topics, and the generated topics' themes and keywords. These topics were categorized into nine main primary themes based on the topic visualization figure. The top three popular themes were prevention and control procedures, medical treatment and research, global/local social/economic influences, accounting for 32.6%, 16.6%, 11.8% of the collected reports respectively.
CONCLUSIONS:
Topic modeling of news articles can produce useful information about the significance of mass media for early health communication. Comparing the number of articles each day and the outbreak development, we note that mass media news reports in China lag behind the development of COVID-19. The major themes accounted for around half the content and tended to focus on the larger society than on individuals. The COVID-19 crisis has become a global issue, and society has also become concerned about donation and support as well as mental health. We recommend that future work should address the mass media's actual impact on readers during the COVID-19 crisis through sentiment analysis of news data.
PMID:32302966DOI:10.2196/19118