Can Twitter Help to Predict Heart Disease?

Can Twitter Help to Predict Heart Disease?

Can Twitter Help to Predict Heart Disease?

Massive social media websites such as Twitter and Facebook are of increasing interesting to social science researchers, as a huge source of data they can quickly reveal trends that would be difficult to otherwise show.

We have already discussed that Facebook may be able to Help People to Stop Smoking and that Twitter can help to Combat Sexism but new research aimed to examine if twitter could help to predict heart disease:

In this study, we analyzed social-media language to identify community-level psychological characteristics associated with mortality from atherosclerotic heart disease (AHD)

On the surface of it the methods that the researchers used seem quite simple:

Working with a data set of 10s of millions of Twitter messages (tweets), we used dictionary-based and open-vocabulary analyses to characterize the psychological language correlates of AHD mortality

But considering the scale of the research finding correlations may have been difficult, despite this the research had 3 major findings:

First, language expressed on Twitter revealed several community-level psychological characteristics that were significantly associated with heart-disease mortality risk.

Secondly the researchers found:

Second, use of negative-emotion (especially anger), disengagement, and negative-relationship language was associated with increased risk, whereas positive-emotion and engagement language was protective.

And finally:

Third, our predictive results suggest that the information contained in Twitter language fully accounts for—and adds to—the AHD-relevant information in 10 representatively assessed demographic, socioeconomic, and health variables

In conclusion the authors of the research suggest that the language used on Twitter can provide a plausible indicator of community-level psychosocial health and that they demonstrated specifically how this may be possible in relation to the risk of cardiovascular mortality.