Study: Tweets Can Predict Health Insurance Exchange Enrollment

March 6, 2015 in News

The sentiment expressed in tweets within a geographic region correlates with health insurance exchange enrollment for that area, according to a study published in the Journal of Medical Internet Research, MedCity News reports (Verel, MedCity News, 3/5).

Study Details

For the study, researchers from the University of Pennsylvania’s Perelman School of Medicine examined 977,303 tweets related to the Affordable Care Act. The researchers looked at tweets directed at’s Twitter account, as well as tweets directed at the accounts of the 17 state-based exchanges in March 2014 (Penn Medicine release, 3/4).

The researchers then compared the sentiment expressed in the tweets with exchange enrollment on a state-by-state basis (MedCity News, 3/5).

The researchers determined tweet sentiment by using the National Research Council sentiment lexicon, which assigns sentiment weights ranging from positive to negative for more than 54,000 words. The researchers said they validated the sentiment lexicon by having human testers rate a random sampling of 300 of the tweets (Penn Medicine release, 3/4).

Study Findings

The researchers found that a 0.10 increase in tweet sentiment scores was associated with a 9% increase in exchange enrollment. They said the numbers “indicate a significant correlation between Twitter sentiment and enrollment based on a continuum of sentiment scores that were examined over a million tweets.”

Overall, they concluded that the sentiment of tweets can operate as a “real-time gauge of public opinion” that could help exchanges identify changes and issues in enrollment.

Further, senior author Raina Merchant — director of the Penn Social Media and Health Innovation Lab and assistant professor of emergency medicine — said the study could have implications beyond Twitter trends. She said the methodology could be “used to improve health care in real-time as health policy is implemented, in order to stay on top of any issues and adjust accordingly” (MedCity News, 3/5).

Be the first to like.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

Article source:

Be Sociable, Share!
Bookmark and Share

Leave a reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>