Early Detection and Control of the Next Epidemic Wave Using Health Communications: Development of an Artificial Intelligence-Based Tool and Its Validation on COVID-19 Data from the US.

Social media networks highly influence on a broad range of global social life, especially in the context of a pandemic. We developed a mathematical model with a computational tool, called EMIT (Epidemic and Media Impact Tool), to detect and control pandemic waves, using mainly topics of relevance on social media networks and pandemic spread. Using EMIT, we analyzed health-related communications on social media networks for early prediction, detection, and control of an outbreak. EMIT is an artificial intelligence-based tool supporting health communication and policy makers decisions. Thus, EMIT, based on historical data, social media trends and disease spread, offers an predictive estimation of the influence of public health interventions such as social media-based communication campaigns. We have validated the EMIT mathematical model on real world data combining COVID-19 pandemic data in the US and social media data from Twitter. EMIT demonstrated a high level of performance in predicting the next epidemiological wave (AUC = 0.909, F1 = 0.899).

Change in Threads on Twitter Regarding Influenza, Vaccines, and Vaccination During the COVID-19 Pandemic: Artificial Intelligence-Based Infodemiology Study.

BACKGROUND: Discussions of health issues on social media are a crucial information source reflecting real-world responses regarding events and opinions. They are often important in public health care, since these are influencing pathways that affect vaccination decision-making by hesitant individuals. Artificial intelligence methodologies based on internet search engine queries have been suggested to detect disease outbreaks and population behavior. Among social media, Twitter is a common platform of choice to search and share opinions and (mis)information about health care issues, including vaccination and vaccines. OBJECTIVE: Our primary objective was to support the design and implementation of future eHealth strategies and interventions on social media to increase the quality of targeted communication campaigns and therefore increase influenza vaccination rates. Our goal was to define an artificial intelligence-based approach to elucidate how threads in Twitter on influenza vaccination changed during the COVID-19 pandemic. Such findings may support adapted vaccination campaigns and could be generalized to other health-related mass communications. METHODS: The study comprised the following 5 stages: (1) collecting tweets from Twitter related to influenza, vaccines, and vaccination in the United States; (2) data cleansing and storage using machine learning techniques; (3) identifying terms, hashtags, and topics related to influenza, vaccines, and vaccination; (4) building a dynamic folksonomy of the previously defined vocabulary (terms and topics) to support the understanding of its trends; and (5) labeling and evaluating the folksonomy. RESULTS: We collected and analyzed 2,782,720 tweets of 420,617 unique users between December 30, 2019, and April 30, 2021. These tweets were in English, were from the United States, and included at least one of the following terms: "flu," "influenza," "vaccination," "vaccine," and "vaxx." We noticed that the prevalence of the terms vaccine and vaccination increased over 2020, and that "flu" and "covid" occurrences were inversely correlated as "flu" disappeared over time from the tweets. By combining word embedding and clustering, we then identified a folksonomy built around the following 3 topics dominating the content of the collected tweets: "health and medicine (biological and clinical aspects)," "protection and responsibility," and "politics." By analyzing terms frequently appearing together, we noticed that the tweets were related mainly to COVID-19 pandemic events. CONCLUSIONS: This study focused initially on vaccination against influenza and moved to vaccination against COVID-19. Infoveillance supported by machine learning on Twitter and other social media about topics related to vaccines and vaccination against communicable diseases and their trends can lead to the design of personalized messages encouraging targeted subpopulations' engagement in vaccination. A greater likelihood that a targeted population receives a personalized message is associated with higher response, engagement, and proactiveness of the target population for the vaccination process.

Social Media Engagement and Influenza Vaccination During the COVID-19 Pandemic: Cross-sectional Survey Study.

BACKGROUND: Vaccines are one of the most important achievements of modern medicine. However, their acceptance is only partial, with vaccine hesitancy and refusal representing a major health threat. Influenza vaccines have low compliance since repeated, annual vaccination is required. Influenza vaccines stimulate discussions both in the real world and online. Social media is currently a significant source of health and medical information. Elucidating the association between social media engagement and influenza vaccination is important and may be applicable to other vaccines, including ones against COVID-19. OBJECTIVE: The goal of this study is to characterize profiles of social media engagement regarding the influenza vaccine and their association with knowledge and compliance in order to support improvement of future web-associated vaccination campaigns. METHODS: A weblink to an online survey in Hebrew was disseminated over social media and messaging platforms. The survey answers were collected during April 2020. Anonymous and volunteer participants aged 21 years and over answered 30 questions related to sociodemographics; social media usage; influenza- and vaccine-related knowledge and behavior; health-related information searching, its reliability, and its influence; and COVID-19-related information searching. A univariate descriptive data analysis was performed, followed by multivariate analysis via building a decision tree to define the most important attributes associated with vaccination compliance. RESULTS: A total of 213 subjects responded to the survey, of whom 207 were included in the analysis; the majority of the respondents were female, were aged 21 to 40 years, had 1 to 2 children, lived in central Israel, were secular Israeli natives, had higher education, and had a salary close to the national average. Most respondents (128/207, 61.8%) were not vaccinated against influenza in 2019 and used social media. Participants that used social media were younger, secular, and living in high-density agglomerations and had lower influenza vaccination rates. The perceived influence and reliability of the information on social media about COVID-19 were generally similar to those perceptions about influenza. CONCLUSIONS: Using social media is negatively linked to compliance with seasonal influenza vaccination in this study. A high proportion of noncompliant individuals can lead to increased consumption of health care services and can, therefore, overload these health services. This is particularly crucial with a concomitant outbreak, such as COVID-19. Health care professionals should use improved and targeted health communication campaigns with the aid of experts in social media. Targeted communication, based on sociodemographic factors and personalized social media usage, might increase influenza vaccination rates and compliance with other vaccines as well.