Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jan 22, 2019
Date Accepted: May 10, 2019
Sentiment analysis of social media on childhood vaccination based on ontology
ABSTRACT
Background:
Although vaccination rates are above the threshold for herd immunity in South Korea, members of the public have expressed concerns about vaccination. It is important to understand these concerns so that we can maintain high vaccination rates.
Objective:
The purpose of this study was to develop a childhood vaccination ontology to serve as a framework for collecting and analyzing social data on childhood vaccination and to then use this ontology to identify public concerns about and sentiments toward childhood vaccination from social data.
Methods:
We determined the scope of the ontology by developing competency questions. Terms were collected from clinical practice guidelines, research papers, and posts on social media platforms. We identified class concepts from these terms and defined hierarchical and attribute relationships between the concepts. The ontology was evaluated in terms of whether it provided accurate answers to the corresponding competency questions. In total, 40,359 Korean posts on childhood vaccination were collected from 27 social media channels between January and December 2015. We grouped terms contained in the post into vaccination issues using an ontology and classified sentiments toward vaccination according to the number of emotional words. Posts were analyzed using frequency, trend, logistic regression, and association rules.
Results:
Childhood vaccination ontology comprised nine superclasses with 137 subclasses, and 431 synonyms for class, attribute and value concepts. ‘Parent's health beliefs’ was posted in 53.21% of posts and positive sentiments appeared in 64.08% of posts. Trends in sentiments toward vaccination were affected by news about vaccinations. Posts with ‘parents' health beliefs’, ‘vaccination availability’, and ‘vaccination policy’ were associated with positive sentiments, whereas posts with ‘experience of vaccine adverse events’ were associated with negative sentiments.
Conclusions:
The childhood vaccination ontology developed in this study was a useful framework for collecting and analyzing social data on childhood vaccination. The findings of this study can be used by the government to develop future policy on childhood vaccination.
Citation
