A Cross-National Study of Fear Appeal Messages in YouTube Trending Videos About COVID-19

The COVID-19 pandemic has underlined the need for investigating the prevalence and nature of health communication on social media. Applying the Extended Parallel Process Model, this study analyzes the use of fear appeals in 2,152 YouTube trending videos across six countries (the United States, Brazil, Russia, Taiwan, Canada, and New Zealand) from January to May 2020. The findings reveal that, during the early stage of the outbreak, COVID-19-themed videos gained early attention in Taiwan but encountered a prolonged delay in the United States and Brazil. Specifically, COVID-19 videos featured the least in Brazil's trending list. The results from a supervised machine learning coding approach further suggest that videos' threat levels exceeded efficacy beliefs across all countries. This imbalance of threat–efficacy messages was most significant in hard-hit countries Brazil and Russia, which social media may run the risk of feeding fear to the public agenda. These findings alert content creators and social media platforms to create a threat–efficacy equilibrium, prioritizing content that promotes a sense of self- and community efficacy and increases people's belief that effective protective actions are available. © 2023 SAGE Publications.

Covering the Crisis: Evolution of Key Topics and Actors in COVID-19 News Coverage in Switzerland

Objectives: The goal of this study is to map the share of COVID-related news articles over time, to investigate key subtopics and their evolution throughout the pandemic, and to identify key actors and their relationship with different aspects of the discourse around the pandemic. Methods: This study uses a large-scale automated content analysis to conduct a within-country comparison of news articles (N = 1,171,114) from two language regions of Switzerland during the first 18 months of the pandemic. Results: News media coverage of the pandemic largely mirrors key epidemiological developments in terms of the volume and content of coverage. Key actors in COVID-related reporting tend to be included in news articles that relate to their respective area of expertise. Conclusion: Balanced news coverage of the pandemic facilitates effective dissemination of pandemic-related information by health authorities. Copyright © 2023 Ort, Rohrbach, Diviani and Rubinelli.

Investigating Opinions on Public Policies in Digital Media: Setting up a Supervised Machine Learning Tool for Stance Classification

Supervised machine learning (SML) provides us with tools to efficiently scrutinize large corpora of communication texts. Yet, setting up such a tool involves plenty of decisions starting with the data needed for training, the selection of an algorithm, and the details of model training. We aim at establishing a firm link between communication research tasks and the corresponding state-of-the-art in natural language processing research by systematically comparing the performance of different automatic text analysis approaches. We do this for a challenging task - stance detection of opinions on policy measures to tackle the COVID-19 pandemic in Germany voiced on Twitter. Our results add evidence that pre-trained language models such as BERT outperform feature-based and other neural network approaches. Yet, the gains one can achieve differ greatly depending on the specific merits of pre-training (i.e., use of different language models). Adding to the robustness of our conclusions, we run a generalizability check with a different use case in terms of language and topic. Additionally, we illustrate how the amount and quality of training data affect model performance pointing to potential compensation effects. Based on our results, we derive important practical recommendations for setting up such SML tools to study communication texts.

Themes & Timing Crisis Communication by German State Governments during the Corona Pandemic – A (Semi-)Automated Content Analysis of Key Communication Channels

The sixteen German states’ crisis communication has played a decisive role throughout the Corona pandemic. This article examines, in an analysis of over 27,000 press releases, tweets, and Facebook posts, the states’ public communication over the first year of this unique, global health crisis. Using (semi-) automated content analysis, it can be shown that content differs depending on the communication channel used: New infection statistics are quickly disseminated via social media while the economic consequences of the pandemic are more frequently addressed through press releases. Using topic modeling, it can also be shown that the state governments each have their own thematic priorities. Over the entire period of the study in 2020, it can be seen that some topics follow the wave-like course of the pandemic in Germany, while others tend to move in the opposite direction. © 2022, Nomos Verlagsgesellschaft mbH und Co KG. All rights reserved.

Health Communication through Positive and Solidarity Messages Amid the COVID-19 Pandemic: Automated Content Analysis of Facebook Uses.

The COVID-19 outbreak has caused significant stress in our lives, which potentially increases frustration, fear, and resentful emotions. Managing stress is complex, but helps to alleviate negative psychological effects. In order to understand how the public coped with stress during the COVID-19 pandemic, we used Macao as a case study and collected 104,827 COVID-19 related posts from Facebook through data mining, from 1 January to 31 December 2020. Divominer, a big-data analysis tool supported by computational algorithm, was employed to identify themes and facilitate machine coding and analysis. A total of 60,875 positive messages were identified, with 24,790 covering positive psychological themes, such as "anti-epidemic", "solidarity", "hope", "gratitude", "optimism", and "grit". Messages that mentioned "anti-epidemic", "solidarity", and "hope" were the most prevalent, while different crisis stages, key themes and media elements had various impacts on public involvement. To the best of our knowledge, this is the first-ever study in the Chinese context that uses social media to clarify the awareness of solidarity. Positive messages are needed to empower social media users to shoulder their shared responsibility to tackle the crisis. The findings provide insights into users' needs for improving their subjective well-being to mitigate the negative psychological impact of the pandemic.