Applying Multiple Data Collection Tools to Quantify Human Papillomavirus Vaccine Communication on Twitter

Abstract

Background: Human papillomavirus (HPV) is the most common sexually transmitted infection in the United States. There are several vaccines that protect against strains of HPV most associated with cervical and other cancers. Thus, HPV vaccination has become an important component of adolescent preventive health care. As media evolves, more information about HPV vaccination is shifting to social media platforms such as Twitter. Health information consumed on social media may be especially influential for segments of society such as younger populations, as well as ethnic and racial minorities.

Objective: The objectives of our study were to quantify HPV vaccine communication on Twitter, and to develop a novel methodology to improve the collection and analysis of Twitter data.

Methods: We collected Twitter data using 10 keywords related to HPV vaccination from August 1, 2014 to July 31, 2015. Prospective data collection used the Twitter Search API and retrospective data collection used Twitter Firehose. Using a codebook to characterize tweet sentiment and content, we coded a subsample of tweets by hand to develop classification models to code the entire sample using machine learning procedures. We also documented the words in the 140-character tweet text most associated with each keyword. We used chi-square tests, analysis of variance, and nonparametric equality of medians to test for significant differences in tweet characteristic by sentiment.

Results: A total of 193,379 English-language tweets were collected, classified, and analyzed. Associated words varied with each keyword, with more positive and preventive words associated with "HPV vaccine" and more negative words associated with name-brand vaccines. Positive sentiment was the largest type of sentiment in the sample, with 75,393 positive tweets (38.99% of the sample), followed by negative sentiment with 48,940 tweets (25.31% of the sample). Positive and neutral tweets constituted the largest percentage of tweets mentioning prevention or protection (20,425/75,393, 27.09% and 6477/25,110, 25.79%, respectively), compared with only 11.5% of negative tweets (5647/48,940; P<.001). Nearly one-half (22,726/48,940, 46.44%) of negative tweets mentioned side effects, compared with only 17.14% (12,921/75,393) of positive tweets and 15.08% of neutral tweets (3787/25,110; P<.001).

Conclusions: Examining social media to detect health trends, as well as to communicate important health information, is a growing area of research in public health. Understanding the content and implications of conversations that form around HPV vaccination on social media can aid health organizations and health-focused Twitter users in creating a meaningful exchange of ideas and in having a significant impact on vaccine uptake. This area of research is inherently interdisciplinary, and this study supports this movement by applying public health, health communication, and data science approaches to extend methodologies across fields.

Keywords: HPV vaccine; Twitter; communication methods; content analysis; data mining.

Figure 1

Flowchart detailing data collection, merging, and cleaning of final dataset of tweets related to human papillomavirus vaccination.

Figure 2

Average area under the receiver operating characteristic curve (AUC) as a function of manually coded tweets.

Figure 3

Percentage of tweets in the final sample by keyword search.