Fight Against the Mandatory COVID-19 Immunity Passport on Twitter: Natural Language Processing Study

Abstract

Background: To contain and curb the spread of COVID-19, the governments of countries around the world have used different strategies (lockdown, mandatory vaccination, immunity passports, voluntary social distancing, etc).

Objective: This study aims to examine the reactions produced by the public announcement of a binding political decision presented by the president of the French Republic, Emmanuel Macron, on July 12, 2021, which imposed vaccination on caregivers and an immunity passport on all French people to access restaurants, cinemas, bars, and so forth.

Methods: To measure these announcement reactions, 901,908 unique tweets posted on Twitter (Twitter Inc) between July 12 and August 11, 2021, were extracted. A neural network was constructed to examine the arguments of the tweets and to identify the types of arguments used by Twitter users.

Results: This study shows that in the debate about mandatory vaccination and immunity passports, mostly "con" arguments (399,803/847,725, 47%; χ²₆=952.8; P<.001) and "scientific" arguments (317,156/803,583, 39%; χ²₆=5006.8; P<.001) were used.

Conclusions: This study shows that during July and August 2021, social events permeating the public sphere and discussions about mandatory vaccination and immunity passports collided on Twitter. Moreover, a political decision based on scientific arguments led citizens to challenge it using pseudoscientific arguments contesting the effectiveness of vaccination and the validity of these political decisions.

Keywords: COVID-19; Twitter; deep learning; effectiveness; immunity; mandatory vaccination; natural language processing; neural network; public health; public health measures; public policy; social distancing; social media; social media analysis; vaccination; vaccine.