Adapting and Extending a Typology to Identify Vaccine Misinformation on Twitter.

Am J Public Health

Amelia M. Jamison, Kajal S. Parikh, and Adeena Malik are with the Maryland Center for Health Equity, School of Public Health, University of Maryland, College Park. David A. Broniatowski and Michael C. Smith are with the Department of Engineering Management and Systems Engineering, School of Engineering and Applied Science, and Institute for Data, Democracy, and Politics, The George Washington University, Washington, DC. Mark Dredze is with the Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD. Sandra C. Quinn is with the Department of Family Science and Maryland Center for Health Equity, School of Public Health, University of Maryland, College Park.

Published: October 2020

To adapt and extend an existing typology of vaccine misinformation to classify the major topics of discussion across the total vaccine discourse on Twitter. Using 1.8 million vaccine-relevant tweets compiled from 2014 to 2017, we adapted an existing typology to Twitter data, first in a manual content analysis and then using latent Dirichlet allocation (LDA) topic modeling to extract 100 topics from the data set. Manual annotation identified 22% of the data set as antivaccine, of which safety concerns and conspiracies were the most common themes. Seventeen percent of content was identified as provaccine, with roughly equal proportions of vaccine promotion, criticizing antivaccine beliefs, and vaccine safety and effectiveness. Of the 100 LDA topics, 48 contained provaccine sentiment and 28 contained antivaccine sentiment, with 9 containing both. Our updated typology successfully combines manual annotation with machine-learning methods to estimate the distribution of vaccine arguments, with greater detail on the most distinctive topics of discussion. With this information, communication efforts can be developed to better promote vaccines and avoid amplifying antivaccine rhetoric on Twitter.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7532318PMC
http://dx.doi.org/10.2105/AJPH.2020.305940DOI Listing

Publication Analysis

Top Keywords

vaccine misinformation
8
existing typology
8
topics discussion
8
data set
8
manual annotation
8
vaccine
6
adapting extending
4
typology
4
extending typology
4
typology identify
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!