Health Policy$ense

Twitter sentiments and ACA enrollment

Twitter, as an indicator of public sentiment, has great potential in health research.  A recent study linked Twitter negativity with rates of heart disease mortality on a county level; a new study links Twitter sentiments with state rates of enrollment on the ACA health insurance marketplaces in the first open enrollment period.

It is important not to overreach, however, in taking correlations beyond the statistical links that they are. One critic notes that being angry on Twitter says nothing about your, or your community’s chances of actually getting heart disease. 

But Twitter can tell us things public opinion polls cannot. First, it can be a barometer of public sentiment in real time, which is advantageous if you want to gauge immediate reaction to a specific event or initiative (say for example, reforms in the National Health Service).  Analyses must account for the echo chamber-like aspects of Twitter (e.g., retweets, modified tweets) that could amplify some sentiments while drowning out others. 

Second, content analysis of publically-available data from Twitter could identify emerging issues and themes for further study, to a degree many orders of magnitude greater than small qualitative inquiries. Analyses must account for the skewed nature of the population on Twitter, and the even more skewed population that uses Twitter regularly.

Third, Twitter can tells us about who the influencers are and how far their networks extend. This could be useful in pushing out health information or a public health message.  Measuring influence, however, is more than just counting followers.

The latest study, conducted by Charlene Wong (@DrCharleneWong) and colleagues at Penn’s Social Media Lab (@PennSoMeLab), is notable for its immediate relevance to ongoing health reform debates. From the paper’s conclusion:

The novel methodology used in our study linking Twitter sentiment to ACA implementation data may be an innovative way to inform how to improve the health care system in real time and may be applicable to other settings as health policy is implemented. As the public debate over the ACA continues and federal and state marketplaces deal with the November 2014 open enrollment session, those managing the marketplaces and monitoring the ACA rollout may consider adding Twitter to their data and evaluation toolkit.