Skip to main content
Add as a preferred source on Google


Collective Digital Traces Could Predict Impact of Emergencies

  • By Dian Schaffhauser
  • 11/06/13

Research undertaken by three institutions has uncovered a link between the number of images posted to photo sharing site Flickr and the intensity of the storm being captured in those Flickr images. The focus of the study was Hurricane Sandy, which hit 24 states in late October 2012. New Jersey was among those hardest hit.

Researchers from the United Kingdom-based Warwick Business School, University College London, and Boston University found that as the number of images posted to Flickr grew, the atmospheric pressure in New Jersey dropped by a comparable degree, portending the peak of the storm.

  New research suggests that digital traces, such as the number of photos uploaded to Flickr referencing Hurricane Sandy, could help researchers predict the consequences of natural disasters and other real-world events.
New research suggests that digital traces, such as the number of photos uploaded to Flickr referencing Hurricane Sandy, could help researchers predict the consequences of natural disasters and other real-world events.		  

"Quantifying the Digital Traces of Hurricane Sandy on Flickr," published this week in Scientific Reports, stated that 32 million photos were posted on Flickr tagged "Hurricane Sandy," "hurricane," or "sandy" between October 20 and November 20. The highest number of images appeared on the site in the same hour in which Hurricane Sandy made landfall in New Jersey.

The report suggested that using online indicators similar to this one could help governments measure the impact of disasters.

Warwick researchers Tobias Preis, associate professor of behavioral science and finance, and Suzy Moat, assistant professor of Behavioral Science, led the project. Both have previously been involved in other projects to find connections between what people seek out online and what they're experiencing in the real world. For example, the frequency with which online visitors search for financial information on Google and Wikipedia could be used as a signal of stock market shifts.

"This study would suggest that in cases where no external sensors are available, it may be possible to use the number of Flickr photos relating to a topic to gauge the current level of this category of problems. Flickr can be considered as a system of large-scale real-time sensors, documenting collective human attention. Increases in Flickr photo counts with particular labels may reveal notable increases in attention to a particular issue, which in some cases may merit further investigation for policy makers," said Moat. "Appropriate leverage of such online indicators of large disasters could be useful to policy makers and others charged with emergency crisis management: in particular if no secondary environmental measures are available."

About the Author

Dian Schaffhauser is a former senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning.

Featured

  • Minimalist binary data fragmentation

    Fragmented Data Is Quietly Undermining Student Success and Cybersecurity Hygiene

    Siloed tools, teams, budgets, and resources spread across departments and campuses generate massive amounts of data. However, fragmentation creates unnecessary exposure to security threats and inadvertently reduces student support because no one can see the whole picture.

  • digital brain with network connections

    Microsoft Moving to Internally Developed AI Models in Office Apps

    Microsoft is reportedly using its own in-house artificial intelligence models to handle some workloads in Excel and Outlook, offering new evidence that the company is moving its AI strategy beyond model development and into large-scale cost reduction.

  • AI user wearing orange safety vest

    California Governor Proposes Independent Watchdogs Within AI Safety System

    California Governor Gavin Newsom is proposing a new model of artificial intelligence regulation that would give independent organizations a formal role in evaluating the safety claims made by leading AI companies.

  • circuit patterns

    Anthropic Launches Lower-Cost Claude Sonnet 5

    Anthropic has released Claude Sonnet 5, positioning the model as its most autonomous mid-tier offering to date and a lower-cost alternative to its flagship Opus 4.8 system. The company said the model can plan multi-step tasks, operate tools such as browsers and terminals, and complete agentic work at a level that previously required larger and more expensive models.