In the minutes and hours following the recent earthquakes in New Zealand and in Japan, and storm in Haiti, thousands of locals posted pictures to social media sites like Facebook and Twitter. These pictures when coupled with extremely granular spatio-temporal information (e.g., timestamps and GPS-style geocodes) provide a minute-by-minute and region-by-region pictorial account of the emergency as it unfolded. The goal of this project is to assess, characterize, and model the quality of these images posted to social media in the minutes and hours post-emergency for guiding policy-based stakeholders and assets. Carefully framed images can convey a wealth of structural information to recovery experts: revealing damage levels, guiding resource allocation, and directing other policy-based assets. First, a sample of several thousand social media images from New Zealand will be assessed by domain experts and specifically structural earthquake engineers. Second, with RAPID funding, this project will link images posted during the emergency to actual damage assessments made in Christchurch for validating the quality of images. First, a sample of several thousand social media images from New Zealand will be assessed by domain experts and specifically structural earthquake engineers. The results of this project will have broad impacts, particularly in the development and deployment of a new rapid assessment tool for earthquake damage assessment based on social media. An additional broader impact is the ancillary development of training modules for increasing the effectiveness and image quality of future socially-generated image capture, which would greatly improve social computing for disasters. The methods and data generated by this project will be archived and made available for future studies.
This project is an initial investigation to assess the quality, coverage, and capacity of social media in the immediate aftermath of an earthquake. Social media – when coupled with extremely granular spatio-temporal information (e.g., timestamps and GPS-style geocodes) – provides a minute-by-minute and region-by-region account of an earthquake as it unfolds. But is social media useful for conveying damage information with respect to structural experts? With NSF support, we have (i) sampled social media data associated with the March 2011 Tohoku earthquake in Japan and the February 2011 Christchurch earthquake in New Zealand; (ii) assessed and modeled the spatio-temporal coverage of social media, and studied the density and dynamics of social media; (iii) linked the social media observations with structural theory; and (iv) begun development of a unified text+image method for identifying affected areas based on the content of tweets and then extracting images from tweets posted in these areas to augment the damage, death, and downtime (3D) model. Our findings of a relationship between social media activity vs. loss/damage attenuation tentatively suggests that social media following a catastrophic event has the potential to provide rapid insight into the extent of damage to be expected in the field, and that this relationship can then be used to infer the locations of greatest damage, as well as where to best deploy emergency response and recovery resources.
