2014.ISDS.Abstracts.Final.pdf


ISDS Annual Conference Proceedings 2014. This is an Open Access article distributed under the terms of the Creative Commons Attribution-
Noncommercial 3.0 Unported License (http://creativecommons.org/licenses/by-nc/3.0/), permitting all non-commercial use, distribution, 
and reproduction in any medium, provided the original work is properly cited.

ISDS 2014 Conference Abstracts

Geo-based Social Media Analytics and SMART 
Dashboard for Tracking Influenza Outbreaks

Ming-Hsiang Tsou1, 3, 4, Michael Peddecord*1, 2, 3, Jeffrey Johnson5, 6 and Chin-Te Jung1, 3, 4

1Graduate School Public Health, San Diego State University, San Diego, CA, USA; 2Quality Health Analytics, San Diego, CA, USA; 
3Center for Human Dynamics in the Mobile Age, San Diego, CA, USA; 4Geography Department, San Diego, CA, USA; 5Epidemiology 
& Immunization Branch, San Diego, CA, USA; 6San Diego County Health and Human Services Agency, San Diego, CA, USA

Objective
We developed geo-targeted social media application program 

interfaces (APIs) for Twitter and a web-based social media analytics 
and research testbed (SMART) dashboard to analyze “flu” related 
tweets. During the 2013-14 flu season, for 10 cities with active 
surveillance for influenza (ILI), we correlated weekly tweeting rates 
and visual patterns of flu tweeting rates. To facilitate widespread 
use and testing of this system, we developed an interactive web-
based dashboard “SMART” that allows practitioners to monitor and 
visualize daily changes of flu trends and related flu news.

Introduction
Active surveillance for influenza is a useful but costly endeavor. 

In recent years infoveillance tools have been developed to track and 
analyze data available on the Internet and social media (Eysenbach 
2011). While infoveillance tools have been developed, few tools 
focus on geo-targeted data collection at a local level combined with 
Geographic Information Systems (GIS) capability.

Methods
Tweets are collected continuously with the keyword “flu” using 

customized geo-targeted Twitter Search APIs from 31 U.S. cities 
based on a 17 mile radius from Week 39, 2013 to Week 10, 2014. 
Our model is based on improvement of previous methods (Nagel et 
al., 2013). We compared the temporal patterns of weekly flu tweeting 
rates in each city against the CDC regional ILI data using 2010 census 
data and GIS methods (Tsou et al. 2013). The correlation (r) between 
flu tweeting rates and the regional CDC ILI records were calculated 
and trends were represented graphically. Our online SMART 
dashboard was built by using Python®, JavaScript®, and the Node.
js® platform (Figure 1).

Results
We used regional CDC ILI data to compare each city’s flu tweeting 

rate within each region. Correlation (r-value) between weekly 
aggregated flu tweeting rates and disease occurrence (CDC regional 
ILI rates) were very high in many cities (Examples: Atlanta vs. 
Region-4 ILI r= 0.79, Nashville vs. Region-4 ILI r= 0.93, Chicago vs. 
Region-5 ILI r= 0.75, Detroit vs. Region-5 ILI r= 0.84, Los Angeles 
vs. Region-9 ILI r= 0.88, Seattle vs. Region-10 ILI r= 0.78). We 
also compare weekly confirmed influenza cases from the San Diego 
County public health laboratory with weekly flu tweeting rates in San 
Diego. The r of 0.93 indicates strong correlation of temporal patterns 
between confirmed influenza cases and flu tweeting rates (Figure 2).

Conclusions
Geo-targeted social media analytics with GIS methods are feasible 

to track and monitor flu outbreaks at the local level. A key advantage 
of our tool is the ability to track flu outbreaks automatically every 
day. Capabilities of the SMART dashboard have great potential to 
assist local public health agencies by providing real-time information 
to investigate and make appropriate responses to large-scale disease 
outbreaks.

Figure 1. SMART Dashboard — Realtime Monitoring of “Flu”

Keywords
Influenza; social media; surveillance; infoveillance; GIS

Acknowledgments

This study is partially supported by the National Science Foundation 
Grant # 1028177, “Mapping Cyberspace to Realspace”. We especially 
thank Anoshe Aslam for her data analysis.

References

Tsou, MH et al (2013) Mapping social activities and concepts with social 
media (Twitter) and web search engines (Yahoo and Bing): a case 
study in 2012 US Presidential Election. Cartography and Geo Info 
Sci, 40(4).

Nagel, AC et al. (2013) The complex relationship of realspace events and 
messages in cyberspace: case study of influenza and pertussis using 
tweets. J Med Internet Res, 15(10).

Eysenbach, G. (2011). Infodemiology and infoveillance tracking online 
health information and cyberbehavior for public health. Am J Prev 
Med, 40(5). 154-8.

*Michael Peddecord

E-mail: mpeddeco@mail.sdsu.edu    

Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * (1):e95, 201