The QuakeCoRE funded research project QuakeText: Mapping Earthquake Impacts from text involves developing methods to automatically extract and georeference disaster impacts from social media.

The rapid growth of social media has resulted in substantial disruption to society through increased online social interaction, access to participative, informal media and highly targeted advertising, among other things. However, the disruptive potential of social media for disaster response has yet to be realised. People readily describe disaster events in “real-time” on social media, including information about specific impacts such as infrastructure damage, injured people or dangerous situations, and their geographic locations, but the vast potential of this information to accelerate recovery and restoration post-event is currently lost. Furthermore, real-time access to this information with accurate georeferences (latitude and longitude) would enable better targeted earthquake response and faster recovery. Current methods are limited both in their inability to identify details of fine-grained impacts and to link those impacts to mentioned locations.

Project Objectives

  1. Develop automated methods for extracting information from textual SM posts about specific impacts and where they are located with relation extraction approaches that use multiple features including syntactic language patterns, and deep learning methods.
  2. Develop automated methods to accurately locate tweets and contained impacts, taking into account relative spatial location terms (extending work on the BioWhere project to the disaster [specifically earthquake] domain).
  3. Evaluate the methods developed both quantitatively and qualitatively.

Our Team

Project leader: Dr Kristin Stock (Massey Geoinformatics Collaboratory)

Dr Raj Prasanna (Massey University)

Professor Christopher Jones (Cardiff University)

Dr Emma Hudson-Doyle (Massey University)

Nishantha Medagoda (Suncorp NZ)

Richard Mowll (Wellington Lifelines Group)

Aaron Tregoweth (NZ Defence Force)

Gavin Treadgold (Canterbury Civil Defence Emergency Mgmt Group)

Aaron Waterreus (Fire & Emergency NZ)

Postgraduate Students

Sameeah Hameed

Harikamba Yandamuri (Cardiff University)

Dukang Li (Cardiff University)

Sophie Francis (Massey University)

Project Outputs

Francis, S., Stock, K., Prasanna, R., Jones, C., Hudson-Doyle, E., Aflaki, N., Medagoda, N., Mowll, R., Tregoweth, A., Treadgold, G. and Waterreus, A. (2022).  QuakeText: Mapping Earthquake Impacts from Text. Poster to be presented at the QuakeCoRE Annual Meeting 2022, 29 August – 1 September, Napier, New Zealand.

Aflaki, N., Stock, K., Prasanna, R., Jones, C.B., Hudson-Doyle, E., Medagoda, N.  QuakeText: Mapping Earthquake Impacts from Text. Lightning talk presented at the New Zealand Geospatial Research Conference, 29-30 August, Wellington, New Zealand.