skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Forecasting influenza-like illness dynamics for military populations using neural networks and social media

Abstract

This work is the first to take advantage of recurrent neural networks to predict influenza-like-illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data [1, 2] and the state-of-the-art machine learning models [3, 4], we build and evaluate the predictive power of Long Short Term Memory (LSTMs) architectures capable of nowcasting (predicting in \real-time") and forecasting (predicting the future) ILI dynamics in the 2011 { 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, stylistic and syntactic patterns, emotions and opinions, and communication behavior. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks. Finally, we combine ILI and social media signals to build joint neural network models for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance [1], specifically for military rather than general populations [3] in 26 U.S. and six international locations. Our approach demonstrates several advantages: (a) Neural network models learned from social media data yield the bestmore » performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than syntactic and stylistic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns.« less

Authors:
ORCiD logo [1];  [1];  [1];  [1];  [1]
  1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1426366
Report Number(s):
PNNL-SA-124148
Journal ID: ISSN 1932-6203; 453040142
Grant/Contract Number:  
AC05-76RL01830
Resource Type:
Accepted Manuscript
Journal Name:
PLoS ONE
Additional Journal Information:
Journal Volume: 12; Journal Issue: 12; Journal ID: ISSN 1932-6203
Publisher:
Public Library of Science
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; neural networks; social media; forecasting influenza dynamics; natural language processing; machine learning

Citation Formats

Volkova, Svitlana, Ayton, Ellyn, Porterfield, Katherine, Corley, Courtney D., and Chowell, Gerardo. Forecasting influenza-like illness dynamics for military populations using neural networks and social media. United States: N. p., 2017. Web. doi:10.1371/journal.pone.0188941.
Volkova, Svitlana, Ayton, Ellyn, Porterfield, Katherine, Corley, Courtney D., & Chowell, Gerardo. Forecasting influenza-like illness dynamics for military populations using neural networks and social media. United States. doi:10.1371/journal.pone.0188941.
Volkova, Svitlana, Ayton, Ellyn, Porterfield, Katherine, Corley, Courtney D., and Chowell, Gerardo. Fri . "Forecasting influenza-like illness dynamics for military populations using neural networks and social media". United States. doi:10.1371/journal.pone.0188941. https://www.osti.gov/servlets/purl/1426366.
@article{osti_1426366,
title = {Forecasting influenza-like illness dynamics for military populations using neural networks and social media},
author = {Volkova, Svitlana and Ayton, Ellyn and Porterfield, Katherine and Corley, Courtney D. and Chowell, Gerardo},
abstractNote = {This work is the first to take advantage of recurrent neural networks to predict influenza-like-illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data [1, 2] and the state-of-the-art machine learning models [3, 4], we build and evaluate the predictive power of Long Short Term Memory (LSTMs) architectures capable of nowcasting (predicting in \real-time") and forecasting (predicting the future) ILI dynamics in the 2011 { 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, stylistic and syntactic patterns, emotions and opinions, and communication behavior. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks. Finally, we combine ILI and social media signals to build joint neural network models for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance [1], specifically for military rather than general populations [3] in 26 U.S. and six international locations. Our approach demonstrates several advantages: (a) Neural network models learned from social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than syntactic and stylistic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns.},
doi = {10.1371/journal.pone.0188941},
journal = {PLoS ONE},
number = 12,
volume = 12,
place = {United States},
year = {2017},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 7 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

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


Global Disease Monitoring and Forecasting with Wikipedia
journal, November 2014


Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance
journal, October 2015


Text and Structural Data Mining of Influenza Mentions in Web and Social Media
journal, February 2010

  • Corley, Courtney; Cook, Diane; Mikler, Armin
  • International Journal of Environmental Research and Public Health, Vol. 7, Issue 2
  • DOI: 10.3390/ijerph7020596

Wikipedia Usage Estimates Prevalence of Influenza-Like Illness in the United States in Near Real-Time
journal, April 2014


Ebola — A Growing Threat?
journal, October 2014


Multiple Estimates of Transmissibility for the 2009 Influenza Pandemic Based on Influenza-like-Illness Data from Small US Military Populations
journal, May 2013


Long Short-Term Memory
journal, November 1997


Social and News Media Enable Estimation of Epidemiological Patterns Early in the 2010 Haitian Cholera Outbreak
journal, January 2012

  • Chunara, Rumi; Andrews, Jason R.; Brownstein, John S.
  • The American Journal of Tropical Medicine and Hygiene, Vol. 86, Issue 1
  • DOI: 10.4269/ajtmh.2012.11-0597

Guess Who’s Not Coming to Dinner? Evaluating Online Restaurant Reservations for Disease Surveillance
journal, January 2014

  • Nsoesie, Elaine O.; Buckeridge, David L.; Brownstein, John S.
  • Journal of Medical Internet Research, Vol. 16, Issue 1
  • DOI: 10.2196/jmir.2998

Uncovering the relationships between military community health and affects expressed in social media
journal, June 2017


Using Social Media for Actionable Disease Surveillance and Outbreak Management: A Systematic Literature Review
journal, October 2015


Monitoring the Impact of Influenza by Age: Emergency Department Fever and Respiratory Complaint Surveillance in New York City
journal, August 2007


HealthMap: Global Infectious Disease Monitoring through Automated Classification and Visualization of Internet Media Reports
journal, March 2008

  • Freifeld, C. C.; Mandl, K. D.; Reis, B. Y.
  • Journal of the American Medical Informatics Association, Vol. 15, Issue 2
  • DOI: 10.1197/jamia.M2544

Enhancing disease surveillance with novel data streams: challenges and opportunities
journal, October 2015


Account Deletion Prediction on RuNet: A Case Study of Suspicious Twitter Accounts Active During the Russian-Ukrainian Crisis
conference, January 2016

  • Volkova, Svitlana; Bell, Eric
  • Proceedings of the Second Workshop on Computational Approaches to Deception Detection
  • DOI: 10.18653/v1/W16-0801