National and Local Influenza Surveillance through Twitter: An Analysis of the 2012-2013 Influenza Epidemic

By David A. Broniatowski, Michael J. Paul, Mark Dredze. PLoS ONE, 2013

470 citations recorded by the source corpus.

Social media have been proposed as a data source for influenza surveillance because they have the potential to offer real-time access to millions of short, geographically localized messages containing information regarding personal well-being. However, accuracy of social media surveillance systems declines with media attention because media attention increases “chatter” – messages that are about influenza but that do not pertain to an actual infection – masking signs of true influenza prevalence. This paper summarizes our recently developed influenza infection detection algorithm that automatically distinguishes relevant tweets from other chatter, and we describe our current influenza surveillance system which was actively deployed during the full 2012-2013 influenza season. Our objective was to analyze the performance of this system during the most recent 2012–2013 influenza season and to analyze the performance at multiple levels of geographic granularity, unlike past studies that focused on national or regional surveillance. Our system’s influenza prevalence estimates were strongly correlated with surveillance data from the Centers for Disease Control and Prevention for the United States (r = 0.93, p < 0.001) as well as surveillance data from the Department of Health and Mental Hygiene of New York City (r = 0.88, p < 0.001). Our system detected the weekly change in direction (increasing or decreasing) of influenza prevalence with 85% accuracy, a nearly twofold increase over a simpler model, demonstrating the utility of explicitly distinguishing infection tweets from other chatter.

Subfields: Epidemiology

View Paper: https://www.semanticscholar.org/paper/687a6a77fcfe143198c311f734a0d68e00943ceb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

Citations in the corpus

Big Data Research in Information Systems: Toward an Inclusive Research Agenda (2016, background): “Such information has important implications for “real-time” predictive analytics in various application areas, ranging from finance to health (Bollen, Mao, & Zeng, 2011; Broniatowski, Paul, & Dredze, 2014).”
Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance (2015, methodology): “We used the Twitter (TWT) influenza classification system introduced by [25,26], which identifies Twitter messages that express an influenza infection.”
Online and Social Media Data As an Imperfect Continuous Panel Survey (2016, background): “[68] and others attempt to solve this particular problem for influenza with a more nuanced approach to the data, but this lacks of out-of-sample robustness is still dominant in both academic research and practice.”
Interpretable Machine Learning : Lessons from Topic Modeling (2016, background): “with the highest coefficients (from left to right) in two bag-of-words linear regression models trained to estimate weekly flu prevalence based on word counts in health-related tweets (from [4]).”
Statistical physics of vaccination (2016, background): “An increasing fraction of tweets contains geographical information that can be adopted to create models at different granularity going from cities [725] to countries [723, 724, 726, 736].”
A Tale of Cities: Urban Biases in Volunteered Geographic Information (2014, background): “In fact, ignoring the problematic data in the location field of user profiles (Hecht et al. 2011), only around 1-3% of all tweets have latitude and longitude geotags (Morstatter et al. 2013; Broniatowski, Paul, and Dredze 2013).”
Geolocation for Twitter: Timing Matters (2016, background): “Geolocation – the task of identifying a social media message’s location – can support a variety of downstream applications, such as advertising, personalization, event discovery, trend analysis and disease tracking (Watanabe et al., 2011; Hong et al., 2012; Kulshrestha et al., 2012; Broniatowski et ”