Using Machine Learning to Compare Provaccine and Antivaccine Discourse Among the Public on Social Media: Algorithm Development Study

Abstract

Background Despite numerous counteracting efforts, antivaccine content linked to delays and refusals to vaccinate has grown persistently on social media, while only a few provaccine campaigns have succeeded in engaging with or persuading the public to accept immunization. Many prior studies have associated the diversity of topics discussed by antivaccine advocates with the public’s higher engagement with such content. Nonetheless, a comprehensive comparison of discursive topics in pro- and antivaccine content in the engagement-persuasion spectrum remains unexplored. Objective We aimed to compare discursive topics chosen by pro- and antivaccine advocates in their attempts to influence the public to accept or reject immunization in the engagement-persuasion spectrum. Our overall objective was pursued through three specific aims as follows: (1) we classified vaccine-related tweets into provaccine, antivaccine, and neutral categories; (2) we extracted and visualized discursive topics from these tweets to explain disparities in engagement between pro- and antivaccine content; and (3) we identified how those topics frame vaccines using Entman’s four framing dimensions. Methods We adopted a multimethod approach to analyze discursive topics in the vaccine debate on public social media sites. Our approach combined (1) large-scale balanced data collection from a public social media site (ie, 39,962 tweets from Twitter); (2) the development of a supervised classification algorithm for categorizing tweets into provaccine, antivaccine, and neutral groups; (3) the application of an unsupervised clustering algorithm for identifying prominent topics discussed on both sides; and (4) a multistep qualitative content analysis for identifying the prominent discursive topics and how vaccines are framed in these topics. In so doing, we alleviated methodological challenges that have hindered previous analyses of pro- and antivaccine discursive topics. Results Our results indicated that antivaccine topics have greater intertopic distinctiveness (ie, the degree to which discursive topics are distinct from one another) than their provaccine counterparts (t122=2.30, P=.02). In addition, while antivaccine advocates use all four message frames known to make narratives persuasive and influential, provaccine advocates have neglected having a clear problem statement. Conclusions Based on our results, we attribute higher engagement among antivaccine advocates to the distinctiveness of the topics they discuss, and we ascribe the influence of the vaccine debate on uptake rates to the comprehensiveness of the message frames. These results show the urgency of developing clear problem statements for provaccine content to counteract the negative impact of antivaccine content on uptake rates.

Marketplaces of Misinformation: A Study of How Vaccine Misinformation Is Legitimized on Social Media

“…Even on a platform where vaccine misinformation represents a small fraction of the content, algorithmic biases can propagate this misinformation (Shin and Valente 2020) through the presence of "filter bubbles" that expose users only to ideas that they already agree with (Jamison et al 2020). The persuasive influence of these misinformation narratives (Argyris et al 2020), combined with the affordances created by digital technologies to spread information widely (e.g., through bots; Wawrzuta et al 2021), creates the conditions for the massive reach of misinformation on social media.…”

COVID-19 vaccine hesitancy: a social media analysis using deep learning

“…They showed that it was possible to use information about the users that people follow online to help predict their opinions. Finally, other studies also complement sentiment or stance analysis with topic modeling (TM) to automatically identify important topics related to vaccine hesitancy from social media's contents (Argyris et al, 2021;Cotfas et al, 2021;Jiang et al, 2021;Karami et al, 2021;Ma et al 2021;Sear et al, 2020;Tomaszewski et al, 2021). Ma et al (2021) used 3,403,166 tweets collected in a 3-month period (January 2021 to March 2021) to compare two different topic models (Top2Vec and LDA) and identify topics related to vaccine hesitancy in the USA.…”

Classifying COVID-19 vaccine narratives

“…As the importance of understanding and tackling COVID-19 vaccination hesitancy grew, increasing efforts have been made to analyse vaccine narratives and discourses, dissemination of false claims and anti-vaccine groups on social media, resulting in the construction of a number of COVID-19 vaccine-focused datasets, without [11,12] or with annotations about veracity (e.g., true or false information) [13], sentiment (e.g., positive, negative or neutral) [14], stance (e.g., pro-or anti-vaccine) [15,16] or topic category (e.g., vaccine development or side effects) [4,17]. The datasets, consequently, can be used to facilitate the research on COVID-19 vaccine-related online information from different aspects, including fact-checking, sentiment analysis, stance detection, and topic analysis.…”

“…Topics or themes discussed in the vaccine-related narratives and online debates are an essential dimension. State-of-the-art methods for automatic topic analysis fall typically under one of these categories: topic modelling [18][19][20][21], clustering [11,12,16,22], and inductive analysis [4,17]. Topic modelling, represented by Latent Dirichlet Allocation (LDA) [23], is the most commonly used approach at present [18][19][20][21].…”