Network based model of social media big data predicts contagious disease diffusion

Lauren S Elkin, Kamil Topal, Gurkan Bebek
  • Information Discovery and Delivery, August 2017, Emerald
  • DOI: 10.1108/idd-05-2017-0046

Influenza diffusion prediction with using social media data

What is it about?

We predict future influeanza like illnesses (ILI) outbreaks and understand how they are spreading from location to location using social media data, namely, Twitter. We create a network model using neighborhood and airline traffic relationships among the states. Results show that flu-related data aligns well with ILI data from the Centers for Disease Control and Prevention (CDC) and the model can predict accurately the ILI activity.

Why is it important?

Early detection Illnesses systems improve patient care providers. While extensive work has been presented utilizing time-series analysis on single geographies, or post-analysis of highly contagious diseases, no previous work has provided a generalized solution to identify how contagious diseases diffuse across geographies, such as states in the USA.

Perspectives

Gurkan Bebek
Case Western Reserve University

It is a pleasure to be a part of this interesting and helpful paper, which is a comprehensive ILI activity surveillance system. This article will lead more sophisticated ILI activity systems. We have already used social media data, geographic locations, airline traffic in the system. More can be added such as Natural Language Processing, epidemiological diffusion models, CDC data, and using more local geographic boundaries instead of states.

Read Publication

http://dx.doi.org/10.1108/idd-05-2017-0046

The following have contributed to this page: Gurkan Bebek

In partnership with: