Scaling up the discovery of hesitancy profiles by identifying the framing of beliefs towards vaccine confidence in Twitter discourse

Abstract

Our study focused on the discovery of how vaccine hesitancy is framed in Twitter discourse, allowing us to recognize at-scale all tweets that evoke any of the hesitancy framings as well as the stance of the tweet authors towards the frame. By categorizing the hesitancy framings that propagate misinformation, address issues of trust in vaccines, or highlight moral issues or civil rights, we were able to empirically recognize their ontological commitments. Ontological commitments of vaccine hesitancy framings couples with the stance of tweet authors allowed us to identify hesitancy profiles for two most controversial yet effective and underutilized vaccines for which there remains substantial reluctance among the public: the Human Papillomavirus and the COVID-19 vaccines. The discovered hesitancy profiles inform public health messaging approaches to effectively reach Twitter users with promise to shift or bolster vaccine attitudes. Supplementary Information The online version contains supplementary material available at 10.1007/s10865-022-00328-z.

Exploring Public Discussions Regarding COVID-19 Vaccinations on Microblogs in China: Findings from Machine Learning Algorithms

“…Sentiment analysis, as a machine learning technique, is used to detect the positive, negative, or neutral sentiments expressed in a text [ 22 ]. It is typically used to analyze the content of web-based texts [ 11 , 16 , 17 ], and has been increasingly popular in the field of public health and preventive medicine [ 23 , 24 , 25 , 26 , 27 ]. Thus far, there are several sentiment dictionaries such as the English NRC sentiment dictionary and Chinese Emotional Vocabulary Ontology Database of the Dalian University of Technology that have been widely used to uncover sentiments expressed in web texts [ 28 , 29 , 30 , 31 ].…”

Broad perspectives in understanding vaccine hesitancy and vaccine confidence: an introduction to the special issue

“…The authors propose development and testing of interventions that could help to neutralize the impact of false claims on Twitter, including prebunking and debunking messaging. Weinzierl et al ( 2023 ), using a unique, sophisticated multi-step approach to Twitter analysis, sought to characterize HPV and COVID-19 vaccination hesitancy and confidence profiles. They note that their innovative methodology enabled them to capture the heterogeneous sets of attitudes that make up vaccine hesitancy and confidence profiles and discuss the implications for more effectively tailoring health messaging based on the identified profiles.…”