Tag Archives: 911

Social Media for Emergency Management: Question of Supply and Demand

I’m always amazed by folks who dismiss the value of social media for emergency management based on the perception that said content is useless for disaster response. In that case, libraries are also useless (bar the few books you’re looking for, but those rarely represent more than 1% of all the books available in a major library). Does that mean libraries are useless? Of course not. Is social media useless for disaster response? Of course not. Even if only 0.001% of the 20+ million tweets posted during Hurricane Sandy were useful, and only half of these were accurate, this would still mean over 1,000 real-time and informative tweets, or some 15,000 words—i.e., the equivalent of a 25-page, single-space document exclusively composed of fully relevant, actionable & timely disaster information.


Empirical studies clearly prove that social media reports can be informative for disaster response. Numerous case studies have also described how social media has saved lives during crises. That said, if emergency responders do not actively or explicitly create demand for relevant and high quality social media content during crises, then why should supply follow? If the 911 emergency number (999 in the UK) were never advertised, then would anyone call? If 911 were simply a voicemail inbox with no instructions, would callers know what type of actionable information to relay after the beep?

While the majority of emergency management centers do not create the demand for crowdsourced crisis information, members of the public are increasingly demanding that said responders monitor social media for “emergency posts”. But most responders fear that opening up social media as a crisis communication channel with the public will result in an unmanageable flood of requests, The London Fire Brigade seems to think otherwise, however. So lets carefully unpack the fear of information flooding.

First of all, New York City’s 911 operators receive over 10 million calls every year that are accidental, false or hoaxes. Does this mean we should abolish the 911 system? Of course not. Now, assuming that 10% of these calls takes an operator 10 seconds to manage, this represents close to 3,000 hours or 115 days worth of “wasted work”. But this filtering is absolutely critical and requires human intervention. In contrast, “emergency posts” published on social media can be automatically filtered and triaged thanks to Big Data Analytics and Social Computing, which could save time operators time. The Digital Operations Center at the American Red Cross is currently exploring this automated filtering approach. Moreover, just as it is illegal to report false emergency information to 911, there’s no reason why the same laws could not apply to social media when these communication channels are used for emergency purposes.

Second, if individuals prefer to share disaster related information and/or needs via social media, this means they are less likely to call in as well. In other words, double reporting is unlikely to occur and could also be discouraged and/or penalized. In other words, the volume of emergency reports from “the crowd” need not increase substantially after all. Those who use the phone to report an emergency today may in the future opt for social media instead. The only significant change here is the ease of reporting for the person in need. Again, the question is one of supply and demand. Even if relevant emergency posts were to increase without a comparable fall in calls, this would simply reveal that the current voice-based system creates a barrier to reporting that discriminates against certain users in need.

Third, not all emergency calls/posts require immediate response by a paid professional with 10+ years of experience. In other words, the various types of needs can be triaged and responded to accordingly. As part of their police training or internships, new cadets could be tasked to respond to less serious needs, leaving the more seasoned professionals to focus on the more difficult situations. While this approach certainly has some limitations in the context of 911, these same limitations are far less pronounced for disaster response efforts in which most needs are met locally by the affected communities themselves anyway. In fact, the Filipino government actively promotes the use of social media reporting and crisis hashtags to crowdsource disaster response.

In sum, if disaster responders and emergency management processionals are not content with the quality of crisis reporting found on social media, then they should do something about it by implementing the appropriate policies to create the demand for higher quality and more structured reporting. The first emergency telephone service was launched in London some 80 years ago in response to a devastating fire. At the time, the idea of using a phone to report emergencies was controversial. Today, the London Fire Brigade is paving the way forward by introducing Twitter as a reporting channel. This move may seem controversial to some today, but give it a few years and people will look back and ask what took us so long to adopt new social media channels for crisis reporting.


Comparing the Quality of Crisis Tweets Versus 911 Emergency Calls

In 2010, I published this blog post entitled “Calling 911: What Humanitarians Can Learn from 50 Years of Crowdsourcing.” Since then, humanitarian colleagues have become increasingly open to the use of crowdsourcing as a methodology to  both collect and process information during disasters.  I’ve been studying the use of twitter in crisis situations and have been particularly interested in the quality, actionability and credibility of such tweets. My findings, however, ought to be placed in context and compared to other, more traditional, reporting channels, such as the use of official emergency telephone numbers. Indeed, “Information that is shared over 9-1-1 dispatch is all unverified information” (1).


So I did some digging and found the following statistics on 911 (US) & 999 (UK) emergency calls:

  • “An astounding 38% of some 10.4 million calls to 911 [in New York City] during 2010 involved such accidental or false alarm ‘short calls’ of 19 seconds or less — that’s an average of 10,700 false calls a day”.  - Daily News
  • “Last year, seven and a half million emergency calls were made to the police in Britain. But fewer than a quarter of them turned out to be real emergencies, and many were pranks or fakes. Some were just plain stupid.” - ABC News

I also came across the table below in this official report (PDF) published in 2011 by the European Emergency Number Association (EENA). The Greeks top the chart with a staggering 99% of all emergency calls turning out to be false/hoaxes, while Estonians appear to be holier than the Pope with less than 1% of such calls.

Screen Shot 2012-12-11 at 4.45.34 PM

Point being: despite these “data quality” issues, European law enforcement agencies have not abandoned the use of emergency phone numbers to crowd-source the reporting of emergencies. They are managing the challenge since the benefit of these number still far outweigh the costs. This calculus is unlikely to change as law enforcement agencies shift towards more mobile-based solutions like the use of SMS for 911 in the US. This important shift may explain why tra-ditional emergency response outfits—such as London’s Fire Brigade—are putting in place processes that will enable the public to report via Twitter.

For more information on the verification of crowdsourced social media informa-tion for disaster response, please follow this link.

Calling 911: What Humanitarians Can Learn from 50 Years of Crowdsourcing

Before emergency telephone numbers existed, one would simply pick up the receiver and say “get me the police” when the operator answered. In fact, operators became the first point of contact for emergency dispatch. They would keep lists of specific numbers in their local towns (local fire department, local doctor, etc) to provide a very personalized emergency service and fast track response.

London was the first city to deploy an emergency number system. The number 999 was launched on June 30, 1937. When called, “a buzzer sounded and a red light flashed in the exchange to attract an operator’s attention” (1). The first number to be used in North America was the 911 system deployed in Winnipeg, Canada in 1959. The first US system, also using the 911 number, was launched in Alabama and Alaska in 1968. It wasn’t until the 1980s, however, that 911 was adopted as the standard number across most of the country.

Today, about 240 million 911 calls are made in the US each year, 30%-50% of which are placed using wireless services, and this number is increasing steadily.

When discussing the use of crowdsourcing to collect crisis information in humanitarian disasters, one of the overriding concerns is: “But what if the information is false? How can we trust that the information reported is true?” We forget that national emergency telephone systems have faced the same challenge for half-a-century. Indeed, 911 is a 50 year-old crowdsourcing system! So our colleagues in law enforcement may have learned a few things during this time, which could inform our work in the humanitarian field.

Incidentally, this may be a silly question but why in the world did governments set up  emergency phone numbers if the information collected using this crowdsourced approach is not immediately verifiable? Have the police gone nuts? What were/are they thinking? Were police crowdsourcing reports before telephone lines sprung up across the country? Maybe one had to run, bike or drive to the police station. Or if you were lucky, perhaps you’d have a police officer strolling the streets at just the right time.

So why not keep that good old analog system then? Well, lets face it, do we really want to leg it to the station every time something’s strange in the neighborhood?  No, we want to be able to call…

Can we assume that we’ll always be mobile during an emergency? Do we want to leave it up to chance that a fire truck might be patrolling the streets when the house next door house goes up in flames? Probably not.

In fact, the world’s oldest emergency (crowdsourcing!) call service—the UK’s 999—was introduced over 70 years ago after a London fire on November 10, 1935 killed 5 women. A neighbor had tried to phone the fire brigade but was held up in a queue by the telephone exchange. Neighbor Norman was so outraged that he wrote a letter to the editor of The Times:

A public outcry resulted (which could have been crowdsourced and mapped on an Ushahidi platform as a complaints mechanism):

This prompted a government inquiry. And thus was born the largest crowdsourcing system of the day. Rather ironic that it was ultimately user generated content that created today’s national emergency phone services. Wouldn’t it be great to get a UN inquiry along those same lines that established a crowdsourcing system for humanitarian crises? Sounds crazy, I know, but hey, 999 probably sounded a little nuts back in 1937 as well. And yet, they decided to test the idea in London, then extended trials in Glasgow and within 10 years the entire country was covered. I don’t see why a similar iterative approach couldn’t work in disaster response.

But what challenges does an emergency phone system face? The misuse and abuse of 911 can be divided into 2 categories: unintentional and intentional calls (2). The former includes phantom calls, misdials and hang-up calls. Lets focus on the latter issue, which be divided into the following categories: Non-emergency Calls, Prank Calls, Exaggerated Calls and Lonely Complainant Calls.

  • Non-emergency Calls: reports suggest that non-emergency calls account for a large percentage of 911 calls. For example, callers will phone in to report their car radio getting stolen, or ask for the results of a football game, the time of day, etc. 911 operators even get callers who ask them to transfer their calls to another number since calling 911 is free.
  • Prank Calls: most agencies apparently do not keep figures on total number of prank calls but these generally come from children and teenagers. Diversionary calls represent a sub-category of prank calls. Callers will dial 911 to send the police to a location where not emergency has occurred, sometimes to divert attention away from criminal activity committed by the caller. “There are only a few ways to determine if a call is diversionary: if the caller admits it; if someone informs on the caller; or if the dispatcher or police compare the caller’s location with that of the alleged emergency, to determine if the caller could plausibly claim an emergency at the called in location” (4).
  • Exaggerated Emergency Calls: callers will sometime intentionally exaggerate the seriousness of an emergency expecting that the police will respond faster. It is reportedly unclear how extensive this problem is.
  • Lonely Complainant Calls: other callers will repeatedly report an emergency over a series of month or years but the police never find evidence of there being one. These calls are often made by the elderly and those with mental health problems.

As these news articles here & here show, false reports to 911 can claim lives. Does this mean that law enforcement is considering pulling the plug on the 911 system? Of course not. So how does law enforcement deal with all this? Lets stick to prank and diversionary calls since this comes closest to the most pressing concerns we face in the humanitarian context. (Note the other issues listed above are typically addressed by educating the public).

Law enforcement’s response to prank calls involves targeting violators and applying graduated sanctions, such as fines or jail time. In Ohio, a public service announcement made clear to users that “we know where you are” when you call 911. Prank calls reportedly dropped as a result (5). Police can also take action by targeting specific phones that are used for prank calls. In another example, a hotel in Vegas routed all 911 calls to hotel security for triage after a large number of false 911 reports were made to the fire department.

Could we do something similar within a humanitarian operation? There’s already precedent to prosecute hate-based SMS, as happened in Kenya. We could work with telcos in question to send out a mass SMS broadcast to all subscribers letting them know they can be prosecuted for deliberately reporting false information.

That’s not a silver bullet, of course, but it seems to help national emergency phone systems. We could also draw on natural language processing (NLP) technologies like Swift River to create veracity ratings for crowdsourced reports. Of course, when confronted with a major disaster, everyone may be calling 911 at the same time, thus overwhelming capacity to respond.

In terms of this operational response, one partial answer may be revitalizing Community Emergency Response Teams (CERTs). Another partial answer may be the idea of crowdfeeding, or crowdsourcing response as I blogged about here based on a recent presentation I gave at Red Cross Conference in DC. During that same conference, the Red Cross revealed the results of a study on the role of social media in emergencies, which showed that more than 70% of those surveyed expect a response within an hour after posting a request on an social media platform. Now, there are too few disaster response professionals to assign to every street to meet those expectations (not to mention the cost implications). So they can’t always be there, but the crowd, by definition, is always there.

In the case of national phone emergency systems, there are usually laws that require the police to respond (not that they always do). This may be difficult to work out in the context of humanitarian response. So let me share an anecdote from the Ushahidi-Haiti Project. One of our overriding concerns after launching the 4636 short code with colleagues was raising expectations among those texting that someone would respond to these SMS’s. Three points:

1) Colleagues and I spent hours on Haitian Diaspora radio and television answering questions from listeners and viewers about the purpose of 4636. We made it very clear that the service was simply an information service and that we couldn’t guarantee any kind of response. We also explained that some responders like the US Coast Guard and Marine Corps were prioritizing life and death situations and therefore were not responding to every text message. This helped callers understand the purpose and limits of the service.

2) As a result of these concerns regarding expectations, my colleague Jaroslav Valuch and I recommended that PakReport.org adjust their public messaging campaign by asking people to report their observations instead of their needs. One could also invite people to text in their complaints, thus crowdsourcing perceptions (real or otherwise) of frustration and discontent which could provide humanitarians with important situational awareness. But this too may raise expectations of response. So sticking with simple reports based on observations is sometimes more prudent.

3) As studies from Aceh (the 2004 tsunami) and Pakistan (the 2005 earthquake) showed, it is important to communicate with disaster affected communities, even if the message is that help is not yet on the way. See Imogen Hall’s research and the CDAC consortium, for example.

I’m using the 911 emergency system as an analogy and don’t pretend that the model can be automatically applied to the humanitarian context. But these phone-based emergency crowdsourcing systems have been around for half-a-century and it would be naive to discount any of the lessons learned and best practices that this wealth of experience has produced across such a large scale.