Abstract
AbstractTwitter data are a valuable source of information for rescue and helping activities in case of natural disasters and technical accidents. Several methods for disaster‐ and event‐related tweet filtering and classification are available to analyse social media streams. Rather than processing single tweets, taking into account space and time is likely to reveal even more insights regarding local event dynamics and impacts on population and environment. This study focuses on the design and evaluation of a generic workflow for Twitter data analysis that leverages that additional information to characterize crisis events more comprehensively. The workflow covers data acquisition, analysis and visualization, and aims at the provision of a multifaceted and detailed picture of events that happen in affected areas. This is approached by utilizing agile and flexible analysis methods providing different and complementary views on the data. Utilizing state‐of‐the‐art deep learning and clustering methods, we are interested in the question, whether our workflow is suitable to reconstruct and picture the course of events during major natural disasters from Twitter data. Experimental results obtained with a data set acquired during hurricane Florence in September 2018 demonstrate the effectiveness of the applied methods but also indicate further interesting research questions and directions.
Highlights
Twitter enables users to post tweets containing text, images and videos with their current locations shared
For a comparison of the obtained insights regarding local and general impacts of hurricane Florence on the population located in the defined area, reference information from the freely accessible news databases GDELT (GDELT Project, 2019), Europe Media Monitor (EMM) (Europe Media Monitor, 2019) and Wikipedia (Wikipedia, 2019), and situation reports published by Humanity Road (Humanity Road, 2019) is used
The results demonstrate that space–time kernel density estimation (STKDE) is a quite useful approach for visualizing and analysing spatio-temporal distributions of crisis-related Twitter activities
Summary
Twitter enables users to post tweets containing text, images and videos with their current locations shared. With an average rate of 0.85%−3% tweets being geo-tagged, around 7,000,000 geo-tagged tweets are posted per day (Huang, Li, & Shan, 2018). In several studies and use cases, the great value and importance of analysing social media streams to extract information for supporting rescue and helping activities in case of natural disasters and technical accidents are demonstrated (Imran, Castillo, Diaz, & Vieweg, 2018; Reuter, Hughes, & Kaufhold, 2018). Even though social media can be a useful information source for all phases of natural disaster management, this work focuses on disaster response activities during and immediately after an event has occurred.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have