Tweets speak volumes about flu epidemics in USA

Harshavardhan Achrekar, a PhD candidate advised by Prof. Benyuan Liu, presented his paper titled “Predicting Flu Trends using Twitter Data” at the International Workshop on Cyber-Physical Networking Systems (CPNS) 2011, in conjunction with IEEE INFOCOM 2011, held in Shanghai, China, April 10–15, 2011.

Seasonal influenza epidemics result in about three to five million cases of severe illness and about 250,000 to 500,000 deaths worldwide each year. Reducing the impact of seasonal influenza epidemics and other pandemics such as H1N1 is of paramount importance for public health authorities.

Studies have shown that effective interventions can be taken to contain the epidemics if early detection can be made. The traditional approach employed by the Centers for Disease Control and Prevention (CDC) includes collecting influenza-like illness (ILI) activity data from “sentinel” medical practices, resulting in a one to two-week delay between the time a patient is diagnosed and the moment that data point becomes available in aggregate ILI reports.

In this paper, the authors investigated the use of a novel data source, namely, messages posted on Twitter, to track and predict the level of ILI activity within US population. Their approach treats Twitter users as “sensors” and the collective message exchanges with a mention of flu-based keywords such as “I got Flu” and “down with swine flu” as early indicators and robust predictors of influenza.

Based on the data collected during 2009 and 2010, they found that the volume of flu-related tweets is highly correlated with the number of ILI cases reported by CDC, and can provide real-time assessment of ILI activity.

This work in supported by the National Institutes of Health under a Small Business Innovation Research Award. The co-authors of the paper include Avinash Gandhe, Ssu-Hsin Yu at SSCI and Ross Lazarus at Harvard.

A copy of the paper is available at

Harshavardhan Achrekar presenting at CPNS 2011.

About this Entry

This page contains a single entry by Martin, Fred published on April 21, 2011 11:31 PM.

Five present at New England Undergraduate Computing Symposium was the previous entry in this blog.

Students demonstrate bevy of apps for iOS devices is the next entry in this blog.

Find recent content on the main index or look in the archives to find all content.

Subscribe to feed Subscribe to this blog's feed