Chapter Fifteen: Big Data and Humanitarian Response
← 210 | 211 → CHAPTER FIFTEEN
Big Data and Humanitarian Response
The overflow of information generated during disasters can be as paralyzing to humanitarian response as the absence of information. This overflow, “Big Data” (or Big Crisis Data), is driven by the massive volume of user-generated content publicly shared on social media platforms like Facebook, Twitter, Instagram, and YouTube. Recent empirical studies demonstrate that some of this content is directly relevant, informative, and even actionable for humanitarian response purposes. In other words, social media can accelerate the assessment of disaster damage and needs during disasters. The challenge, however, is that only a very small fraction of user-generated content presently adds to situational awareness. But this content could potentially be life-saving information. During Typhoon Yolanda in November 2013, for example, barely ~0.25% of the quarter-of-a-million tweets posted during the first 72 hours were informative and/or actionable. While this seems insignificant, 0.25% represents more than 600 geo-tagged tweets, or more than 60,000 words of relevant and timely information for disaster responders. Of the 5,000+ images posted to Twitter, only ~3.5% captured infrastructure damage cause by the Typhoon—but this still represents 180 individual geo-tagged pictures available in real-time. So identifying this content is like looking for the proverbial needle in the haystack—the growing stack of information generated during disasters.
Assuming that one person was tasked with reviewing each of the 250,000+ tweets, it would have taken that person well over...
You are not authenticated to view the full text of this chapter or article.
This site requires a subscription or purchase to access the full text of books or journals.
Do you have any questions? Contact us.Or login to access all content.