You Are What You Tweet: Analyzing Twitter for Public Health

TLDR

Social media data can capture population health signals, and prior studies have linked Twitter content to influenza rates, but such mining has been limited to a narrow set of public health indicators. This study expands Twitter’s use to a broader spectrum of public health applications. The authors applied an extended Ailment Topic Aspect Model to over 1.5 million health‑related tweets, incorporating prior knowledge to track temporal syndromes, assess behavioral risk factors, map geographic illness prevalence, and analyze symptom and medication mentions. The model produced quantitative correlations with official public health data and qualitative evidence that Twitter can serve as a versatile tool for public health research.

Abstract

Analyzing user messages in social media can measure different population characteristics, including public health measures. For example, recent work has correlated Twitter messages with influenza rates in the United States; but this has largely been the extent of mining Twitter for public health. In this work, we consider a broader range of public health applications for Twitter. We apply the recently introduced Ailment Topic Aspect Model to over one and a half million health related tweets and discover mentions of over a dozen ailments, including allergies, obesity and insomnia. We introduce extensions to incorporate prior knowledge into this model and apply it to several tasks: tracking illnesses over times (syndromic surveillance), measuring behavioral risk factors, localizing illnesses by geographic region, and analyzing symptoms and medication usage. We show quantitative correlations with public health data and qualitative evaluations of model output. Our results suggest that Twitter has broad applicability for public health research.