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

Dr. Arriel Benis, Senior Lecturer Faculty of Industrial Engineering and Technology Management, HIT

Session II: March 30^th, 13:25-13:45

Discussions of health issues on social media are a crucial information source reflecting real-world responses regarding events and opinions. They are critical in public health care, since they influence vaccination hesitancy. AI-based studies on internet search engine queries suggested detecting disease outbreaks and population behavior. Twitter is a platform of choice among social media to search and share opinions and (mis)information about health care issues, including vaccination and vaccines.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 AI-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. The study comprised five stages: 1. collecting tweets related to influenza, vaccines, and vaccination; 2. data cleansing using machine learning techniques; 3. identifying terms, hashtags, and topics related to influenza, vaccines, and vaccination; 4. building a folksonomy of the discovered vocabulary; and 5. labeling and evaluating the folksonomy. We collected and analyzed 2,782,720 tweets in English from the US of 420,617 unique users between 30/12/2019 and 30/04/2021, comprising at least one of the following terms: “flu,” “influenza,” “vaccination,” “vaccine,” and “vaxx.” We built, with word embedding and clustering, a folksonomy of three dominant topics: “health and medicine,” “protection and responsibility,” and “politics.” Infoveillance supported by machine learning on Twitter and other social media about 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 customized message is associated with higher response, engagement, and proactiveness for the vaccination process.