Liu Qian, Zheng Zequan, Zheng Jiabin, Chen Qiuyi, Liu Guan, Chen Sihan, Chu Bojia, Zhu Hongyu, Akinwunmi Babatunde, Huang Jian, Zhang Casper J P, Ming Wai-Kit
School of Journalism and Communication, National Media Experimental Teaching Demonstration Center, Jinan University, Guangzhou, Guangdong Province, China.
Department of Communication, University at Albany, State University of New York, Albany, New York State, NY, United States.
J Med Internet Res. 2020 Apr 28;22(4):e19118. doi: 10.2196/19118.
In December 2019, a few coronavirus disease (COVID-19) cases were first reported in Wuhan, Hubei, China. Soon after, increasing numbers of cases were detected in other parts of China, eventually leading to a disease outbreak 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, prevention, and containment.
The aim of this study was to collect media reports on COVID-19 and investigate the patterns of media-directed health communications as well as the role of the media in this ongoing COVID-19 crisis in China.
We adopted the WiseSearch database to extract related news articles about the coronavirus from major press media between January 1, 2020, and February 20, 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 topic modeling with a suitable topic number and generated corresponding keywords and topic names. We then divided these topics into different themes by plotting them into a 2D plane via multidimensional scaling.
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 the number of topics and generated the topics' themes and keywords. These topics were categorized into nine main primary themes based on the topic visualization figure. The top three most popular themes were prevention and control procedures, medical treatment and research, and global or local social and economic influences, accounting for 32.57% (n=2538), 16.08% (n=1258), and 11.79% (n=919) of the collected reports, respectively.
Topic modeling of news articles can produce useful information about the significance of mass media for early health communication. Comparing the number of articles for each day and the outbreak development, we noted that mass media news reports in China lagged behind the development of COVID-19. The major themes accounted for around half the content and tended to focus on the larger society rather than on individuals. The COVID-19 crisis has become a worldwide issue, and society has become concerned about donations and support as well as mental health among others. We recommend that future work addresses the mass media's actual impact on readers during the COVID-19 crisis through sentiment analysis of news data.
2019年12月，中国湖北省武汉市首次报告了几例冠状病毒病（COVID-19）病例。此后不久，中国其他地区检测到的病例数量不断增加，最终导致中国爆发了疫情。随着这种可怕的疾病迅速蔓延，大众媒体通过提供有关这种新型冠状病毒的健康信息，如发病机制、传播、预防和控制等，积极开展关于COVID-19的社区教育。
本研究旨在收集关于COVID-19的媒体报道，调查媒体导向的健康传播模式以及媒体在中国当前COVID-19危机中的作用。
我们采用WiseSearch数据库，从2020年1月1日至2020年2月20日期间的主要新闻媒体中提取有关冠状病毒的相关新闻文章。然后，我们使用Python软件和Python包结巴对数据进行分类和分析。我们寻找具有连贯性数字证据的合适主题数量。我们使用合适的主题数量运行潜在狄利克雷分配主题建模，并生成相应的关键词和主题名称。然后，我们通过多维缩放将这些主题绘制到二维平面中，将它们分为不同的主题。
在去除重复和无关报道后，我们的搜索确定了7791篇相关新闻报道。我们列出了每天发表的文章数量。根据连贯性值，我们选择20作为主题数量，并生成了主题的主题和关键词。根据主题可视化图，这些主题被分为九个主要的初级主题。最受欢迎的前三个主题是防控程序、医疗救治与研究以及全球或本地社会经济影响，分别占所收集报道的32.57%（n = 2538）、16.08%（n = 1258）和11.79%（n = 919）。
新闻文章的主题建模可以产生关于大众媒体在早期健康传播中的重要性的有用信息。通过比较每天的文章数量和疫情发展情况，我们注意到中国的大众媒体新闻报道落后于COVID-19的发展。主要主题约占内容的一半，并且倾向于关注更大的社会而非个人。COVID-19危机已成为一个全球性问题，社会开始关注捐赠与支持以及心理健康等问题。我们建议未来的工作通过对新闻数据的情感分析来解决大众媒体在COVID-19危机期间对读者的实际影响。
