Integration of social media analysis and crowdsourced information within both the Mapping and Early Warning Components of Copernicus Emergency Management Service (EMS)

 

 

M
Methods

Heterogeneous social media data streams (Twitter, Flickr, Facebook, Instagram, etc.) will be analyzed and sparse crowdsourcing communities will be federated (crisis specific as Tomnod, HOT, SBTF and generic as Crowdcrafting, EpiCollect, etc.). E2mC will perform demonstrations within realistic and operational scenarios designed by the users involved within the project (Civil Protection Authorities and Humanitarian Aid operators, including their volunteer teams) and by the current Copernicus EMS Operational Service Providers that are part of the E2mC Consortium. The involvement of social media and crowdsourcing communities will foster the engagement of a large number of people in supporting crisis management and foster increase awareness of Copernicus.

B
Background

Current methods in disaster management, which are greatly based on remote sensing technology, suffer from severe shortcomings including a temporal lag of typically of 48-72 hours, or limited spatial resolution. Thus, the E2mC project aims at demonstrating the technical and operational feasibility of the integration of social media analysis and crowdsourced information within both the Mapping and Early Warning Components of Copernicus Emergency Management Service (EMS).

R
Results

E2mC aims at demonstrating the technical and operational feasibility of the integration of social media analysis and crowdsourced information within both the Mapping and Early Warning Components of Copernicus Emergency Management Service (EMS). The project team will develop a prototype of a new EMS Service Component (Copernicus Witness), designed to exploit social media analysis and crowdsourcing capabilities to generate a new Product of the EMS Portfolio.

 
Project Partners
Team
Bernd Resch (project lead)
Clemens Havas, Jakob Miksch, Oliver Zichert, Stefan Zimmer
Key Publications
Havas C., Resch B., Francalanci C., et al. (2017) E2mC: Improving Emergency Management Service Practice through Social Media and Crowdsourcing Analysis in Near Real Time Sensors 17(12), 2766, DOI: https://doi.org/10.3390/s17122766.
Link
Resch, B., Usländer, F., Havas C. (2018) Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment Cartography and Geographic Information Science, 45(4), 362-376, DOI: https://doi.org/10.1080/15230406.2017.1356242.
Link
Havas C., Resch B. (2021) Portability of semantic and spatial–temporal machine learning methods to analyse social media for near-real-time disaster monitoring Natural Hazards volume 108, pages 2939–2969, DOI: https://doi.org/10.1007/s11069-021-04808-4.
Link