@InProceedings{iso-wakamiya-aramaki:2016:COLING,
  author    = {ISO, Hayate  and  WAKAMIYA, Shoko  and  ARAMAKI, Eiji},
  title     = {Forecasting Word Model: Twitter-based Influenza Surveillance and Prediction},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {76--86},
  abstract  = {Because of the increasing popularity of social media, much information has been
	shared on the internet, enabling social media users to understand various real
	world events. Particularly, social media-based infectious disease surveillance
	has attracted increasing attention. In this work, we specifically examine
	influenza: a common topic of communication on social media. The fundamental
	theory of this work is that several words, such as symptom words (fever,
	headache, etc.), appear in advance of flu epidemic occurrence. Consequently,
	past word occurrence can contribute to estimation of the number of current
	patients. To employ such forecasting words, one can first estimate the optimal
	time lag for each word based on their cross correlation. Then one can build a
	linear model consisting of word frequencies at different time points for
	nowcasting and for forecasting influenza epidemics. Experimentally obtained
	results (using 7.7 million tweets of August 2012 -- January 2016), the
	proposed model achieved the best nowcasting performance to date (correlation
	ratio 0.93) and practically sufficient forecasting performance (correlation
	ratio 0.91 in 1-week future prediction, and correlation ratio 0.77 in 3-weeks
	future prediction). This report is the first of the relevant literature to
	describe a model enabling prediction of future epidemics using Twitter.},
  url       = {http://aclweb.org/anthology/C16-1008}
}