We would like to propose a panel which discusses this paper but includes special guests from the International and Qatar Humanitarian community to talk about the future of humanitarian research in the MENA region. In the new era of data abundance, procedures for crisis and disaster response have changed. As relief forces struggle with assistance on the ground, digital humanitarians step in to provide a collective response at unprecedented shorttime scales, curating valuable bits of information through simple tasks – mapping, tagging, and evaluating. This hybrid emergency response leaves behind detailed traces, which inform data scientists about how far and how fast the calls for action reach volunteers around the globe. Among the few consolidated platforms in the DH technology arena, we find MicroMappers1. It was created at QCRI, partnering with UN-OCHA and the Standby Task Force, as part of a tool set that combines machine learning and human computing: Artificial Intelligence for Disaster Response2 (AIDR) [1]. MicroMappers is activated during natural disasters in order to tag short text messages and evaluate ground and aerial images. Thus, MicroMappers can also be viewed as a valuable data repository, containing historical data from past events in which it was activated. To perform our study, we rely on rich datasets coming from three natural disasters occurring in Philippines (Typhoon Hagupit, 2014) [2], Vanuatu (Cyclone Pam, 2015) [3] and Nepal (earthquake, 2015) [4]. Each event rendered thousands of digital records from the labor inputs of the crowd. We focus particularly on IPaddresses, which can be conveniently mapped to a specific location; and timestamps, which describe for us the unfolding of the collective response in time. The anonymity of each contributor is preserved at all times throughout the project.


Article metrics loading...

Loading full text...

Full text loading...

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error