Modeling the Dynamics of Hurricane Evacuation Decisions from Real-time Twitter Data

Evacuations play a critical role in saving human lives during hurricanes. But individual evacuation decision-making is a complex dynamic process, often studied using post-hurricane survey data. Alternatively, ubiquitous use of social media generates a massive amount of data that can be used to understand evacuation behavior in real-time. In this paper, the authors present a method to infer individual evacuation behaviors (e.g., evacuation decision, timing, destination) from social media data. Previous studies used heuristics to infer such behaviors from geo-tagged tweets. The authors develop an input output hidden Markov model (IO-HMM) to infer evacuation decisions from user tweets during a hurricane. To infer the underlying context from tweet texts, the authors estimate a wod2vec model from a corpus of more than 100 million tweets collected over four major hurricanes. To validate the results, the authors have created ground truth data from hurricane Irma twitter data with 1.81 million tweets from 248,763 unique users. The findings show that the proposed IO-HMM method can be useful in inferring evacuation behavior in real time from social media data. The proposed method infers what decisions are made by individuals, when they decide to evacuate, and where they evacuate to. As traditional survey-based studies are infrequent, costly, and often performed at a post-hurricane period, the proposed method can be very useful to practitioners for predicting evacuation traffic as a hurricane unfolds in real time.

  • Supplemental Notes:
    • This paper was sponsored by TRB committee ABR30 Standing Committee on Emergency Evacuations.
  • Corporate Authors:

    Transportation Research Board

  • Authors:
    • Roy, Kamol Chandra
    • Hasan, Samiul
  • Conference:
  • Date: 2019


  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; References; Tables;
  • Pagination: 8p

Subject/Index Terms

Filing Info

  • Accession Number: 01697974
  • Record Type: Publication
  • Report/Paper Numbers: 19-04479
  • Files: TRIS, TRB, ATRI
  • Created Date: Mar 1 2019 3:51PM