Journal article
CrisisTracker: Crowdsourced social media curation for disaster awareness
J Rogstadius, M Vukovic, CA Teixeira, V Kostakos, E Karapanos, JA Laredo
IBM Journal of Research and Development | IBM CORP | Published : 2013
Abstract
Victims, volunteers, and relief organizations are increasingly using social media to report and act on large-scale events, as witnessed in the extensive coverage of the 2010-2012 Arab Spring uprisings and 2011 Japanese tsunami and nuclear disasters. Twitter® feeds consist of short messages, often in a nonstandard local language, requiring novel techniques to extract relevant situation awareness data. Existing approaches to mining social media are aimed at searching for specific information, or identifying aggregate trends, rather than providing narratives. We present CrisisTracker, an online system that in real time efficiently captures distributed situation awareness reports based on social..
View full abstractGrants
Awarded by Portuguese Foundation for Science and Technology
Awarded by Fundação para a Ciência e a Tecnologia
Funding Acknowledgements
We express our sincere gratitude to all the curators and disaster-response experts who participated in this study. We thank Patrick Meier for promoting the evaluation as a Standby Task Force deployment and for his guidance in crowd management. We also thank Syria Tracker for its support in making the deployment realistic and safe, and for actively using the system in its daily monitoring of the conflict. We thank Rebecca Curzon and Vicki Kraeling for promoting the study with disaster practitioners. Finally, we thank Ko-Hsun Huang for key guidance in gathering, analysis, and interpretation of data. This work is supported by an IBM Open Collaboration Research Award and by the Portuguese Foundation for Science and Technology (grant CMU-PT/SE/0028/2008; Web Security and Privacy).