Emotions and Incivility in Vaccine Mandate Discourse: Natural Language Processing Insights

Abstract

Background Despite vaccine availability, vaccine hesitancy has inhibited public health officials’ efforts to mitigate the COVID-19 pandemic in the United States. Although some US elected officials have responded by issuing vaccine mandates, others have amplified vaccine hesitancy by broadcasting messages that minimize vaccine efficacy. The politically polarized nature of COVID-19 information on social media has given rise to incivility, wherein health attitudes often hinge more on political ideology than science. Objective To the best of our knowledge, incivility has not been studied in the context of discourse regarding COVID-19 vaccines and mandates. Specifically, there is little focus on the psychological processes that elicit uncivil vaccine discourse and behaviors. Thus, we investigated 3 psychological processes theorized to predict discourse incivility—namely, anxiety, anger, and sadness. Methods We used 2 different natural language processing approaches: (1) the Linguistic Inquiry and Word Count computational tool and (2) the Google Perspective application programming interface (API) to analyze a data set of 8014 tweets containing terms related to COVID-19 vaccine mandates from September 14, 2021, to October 1, 2021. To collect the tweets, we used the Twitter API Tweet Downloader Tool (version 2). Subsequently, we filtered through a data set of 375,000 vaccine-related tweets using keywords to extract tweets explicitly focused on vaccine mandates. We relied on the Linguistic Inquiry and Word Count computational tool to measure the valence of linguistic anger, sadness, and anxiety in the tweets. To measure dimensions of post incivility, we used the Google Perspective API. Results This study resolved discrepant operationalizations of incivility by introducing incivility as a multifaceted construct and explored the distinct emotional processes underlying 5 dimensions of discourse incivility. The findings revealed that 3 types of emotions—anxiety, anger, and sadness—were uniquely associated with dimensions of incivility (eg, toxicity, severe toxicity, insult, profanity, threat, and identity attacks). Specifically, the results showed that anger was significantly positively associated with all dimensions of incivility (all P<.001), whereas sadness was significantly positively related to threat (P=.04). Conversely, anxiety was significantly negatively associated with identity attack (P=.03) and profanity (P=.02). Conclusions The results suggest that our multidimensional approach to incivility is a promising alternative to understanding and intervening in the psychological processes underlying uncivil vaccine discourse. Understanding specific emotions that can increase or decrease incivility such as anxiety, anger, and sadness can enable researchers and public health professionals to develop effective interventions against uncivil vaccine discourse. Given the need for real-time monitoring and automated responses to the spread of health information and misinformation on the web, social media platforms can harness the Google Perspective API to offer users immediate, automated feedback when it detects that a comment is uncivil.

Incivility in COVID-19 Vaccine Mandate Discourse and Moral Foundations: Natural Language Processing Approach

“…Ultimately, we argue that the antecedents of incivility can inform public health interventions. Existing studies have found a link between incivility and negative emotions such as sadness and anxiety [ 20 ]. Therefore, public health messaging that evokes such emotions could result in uncivil discourse from the public.…”

“…Perspective application programming interface (API), a tool that uses machine learning to detect comment incivility, was used to measure 5 dimensions of incivility, namely, toxicity, insults, profanity, threat, and identity attack (see Textbox 3 for definitions and examples). Perspective API is a validated tool trained by human coders on large data sets with millions of comments and has been used in studies across various contexts, such as health and politics [ 17 , 20 , 63 , 64 ]. Perspective API assigns each comment a score from 0 to 1 per dimension of incivility based on how closely the comment reflected the specific dimension and how likely it was to impact a conversation.…”

A longitudinal study of the top 1% toxic Twitter profiles

“…Each model, for every given input text, yields a score from 0 to 1 representing the intensity of a type of misbehavior. We retrieve scores from the 6 production-ready Perspective API models [51]:…”

When Patient Rudeness Impacts Care: A Review of Incivility in Healthcare

“…In terms of patient characteristics, some research indicates that the emotional state of a patient greatly influences their likelihood to behave with incivility. Two emotions are most strongly associated with an increased incidence of incivility: anger and sadness [ 14 ]. Specifically, anger has been linked to an increased likelihood of “profanity, insults,... identity attacks, and threats” while sadness increases the likelihood of threats [ 14 ].…”