Social media data and post-disaster recovery

作者：

Highlights：

• Introduce new Machine Learning Algorithm to analyze huge geo-tagged social media data.

• Evaluate the priorities of disaster victims in post-disaster recovery period.

• Predict the priorities based on internal attributes (i.e. Age, income, employment, etc.).

• Compare the results with non-disaster experienced population.

• Offer several paths for future works to improve the methodology.

摘要

•Introduce new Machine Learning Algorithm to analyze huge geo-tagged social media data.•Evaluate the priorities of disaster victims in post-disaster recovery period.•Predict the priorities based on internal attributes (i.e. Age, income, employment, etc.).•Compare the results with non-disaster experienced population.•Offer several paths for future works to improve the methodology.

论文关键词：Temporal–spatial patterns,Post-disaster recovery,Social media,Twitter

论文评审过程：Received 13 December 2017, Revised 15 September 2018, Accepted 15 September 2018, Available online 25 September 2018, Version of Record 25 September 2018.

论文官网地址：https://doi.org/10.1016/j.ijinfomgt.2018.09.005