Tag Archives: Disasters

The Value of Timely Information During Disasters (Measured in Hours)

In the 2005 World Disaster Report (PDF), the International Federation of the Red Cross states unequivocally that access to information during disasters is equally important as access to food, water, shelter and medication. Of all these commodities, however, crisis information is the most perishable. In other words, the “sell-by” or “use-by” date of information for decision-making during crisis is very short. Put simply: information rots fast, especially in the field (assuming that information even exists in the first place). But how fast exactly as measured in hours and days?

Screen Shot 2016-03-31 at 2.49.16 PM

Enter this handy graph by FEMA, which is based on a large survey of emergency management professionals across the US. As you’ll note, there is a very clear cut-off at 72 hours post-disaster by which time the value of information for decision making purposes has depreciated by 60% to 85%. Even at 48 hours, information has lost 35% to 65% of its initial tactical value. Disaster responders don’t have the luxury of waiting around for actionable information to inform their decisions during the first 24-72 hours after a disaster. So obviously they’ll take those decisions whether or not timely data is available to guide said decisions.

In a way, the graph also serves as a “historical caricature” of the availability of crisis information over the past 25 years:

11qsii

During the early 1990s, when the web and mobile phones were still in their infancy, it often took weeks to collect detailed information on disaster damage and needs following major disasters. Towards the end of the 2000’s, thanks to the rapid growth in smartphones, social media and the increasing availability of satellite imagery plus improvements in humanitarian information management systems, the time it took to collect crisis information was shortened. One could say we crossed the 72-hour time barrier on January 12, 2010 when a devastating earthquake struck Haiti. Five years later, the Nepal earthquake in April 2015 may have seen a number of formal responders crossing the 48-hour threshold.

While these observations are at best the broad brushstrokes of a caricature, the continued need for timely information is very real, especially for tactical decision making in the field. This is why we need to shift further left in the FEMA graph. Of course, information that is older than 48 hours is still useful, particularly for decision-makers at headquarters who do not need to make tactical decisions.

Screen Shot 2016-03-31 at 3.29.18 PM

In fact, the real win would be to generate and access actionable information within the first 12- to 24-hour mark. By the end of the 24-hours, the value of information has “only” depreciated by 10% to 35%. So how do we get to the top left corner of the graph? How do we get to “Win”?

Screen Shot 2016-03-31 at 3.31.16 PM

By integrating new and existing sensors and combining these with automated analysis solutions. New sensors: like Planet Lab’s growing constellation of micro-satellites, which will eventually image the entire planet once every 24 hours at around 3-meter resolution. And new automated analysis solutions: powered by crowdsourcing and artificial intelligence (AI), and in particular deep learning techniques to process the Big Data generated by these “neo-sensors” in near real-time, including multimedia posted to social media sites and the Web in general.

And the need for baseline data is no less important for comparative analysis and change detection purposes. As a colleague of mine recently noted, the value of baseline information before a major disaster is at an all time high but then itself depreciates as well post-disaster.

Screen Shot 2016-03-31 at 3.41.18 PM

Of course, access to real-time information does not make a humanitarian organization a real-time response organization. There are always delays regard-less of how timely (or not) the information is (assuming it is even available). But the real first responders are the local communities. So the real win here would be to make make this real-time analysis directly available to local partners in disaster prone countries. They often have more of an immediate incentive to generate and consume timely, tactical information. I described this information flow as “crowdfeeding” years ago.

In sum, the democratization of crisis information is key (keeping in mind data-protection protocols). But said democratization isn’t enough. The know-how and technologies to generate and analyze crisis information during the first 12-24 hours must also be democratized. The local capacity to respond quickly and effectively must exist; otherwise timely, tactical information will just rot away.


I’d be very interested to hear from human rights practitioners to get their thoughts on how/when the above crisis information framework does, and does not, apply when applied to human rights monitoring.

New Findings: Rapid Assessment of Disaster Damage Using Social Media

The latest peer-reviewed, scientific research on social media & crisis computing has just been published in the prestigious journal, Science. The authors pose a question that many of us in the international humanitarian space have been asking, debating and answering since 2009: Can social media data aid in disaster response and damage assessment?

hurricane-sandy-social-media
To answer this question, the authors of the new study carry out “a multiscale analysis of Twitter activity before, during, and after Hurricane Sandy” and “examine the online response of 50 metropolitan areas of the US.” They find a “strong relationship between proximity to Sandy’s path and hurricane-related social media activity.” In addition, they “show that real and perceived threats, together with physical disaster effects, are directly observable through the intensity and composition of Twitter’s message stream.”

Screen Shot 2016-03-17 at 12.18.11 PM

What’s more, they actually “demonstrate that per-capita Twitter activity strongly correlates with the per-capita economic damage inflicted by the hurricane.” The authors found these results to hold true for a “wide range of [US-based] disasters and suggest that massive online social networks can be used for rapid assessment of damage caused by a large-scale disaster.”

Screen Shot 2016-03-17 at 12.26.51 PM

Unlike the vast majority of crisis computing studies in the scientific literature, this is one of the few (perhaps the only?) study of its kind that uses actual post-disaster damage data, i.e. actual ground-truthing, to demonstrate that “the per-capita number of Twitter messages corresponds directly to disaster-inflicted monetary damage.” What’s more, “The correlation is especially pronounced for persistent post-disaster activity and is weakest at the peak of the disaster.”

Screen Shot 2016-03-17 at 1.16.11 PM

The authors thus conclude that social media is a “viable platform for preliminary rapid damage assessment in the chaotic time immediately after a disaster.” As such, their results suggest that “officials should pay attention to normalized activity levels, rates of original content creation, and rates of content rebroadcast to identify the hardest hit areas in real time. Immediately after a disaster, they should focus on persistence in activity levels to assess which areas are likely to need the most assistance.”

Screen Shot 2016-03-17 at 12.37.02 PM

In sum, the authors found that “Twitter activity during a large-scale natural disaster—in this instance Hurricane Sandy—is related to the proximity of the region to the path of the hurricane. Activity drops as the distance from the hurricane increases; after a distance of approximately 1200 to 1500 km, the influence of proximity disappears. High-level analysis of the composition of the message stream reveals additional findings. Geo-enriched data (with location of tweets inferred from users’ profiles) show that the areas close to the disaster generate more original content […].”

Five years ago, professional humanitarians were still largely dismissive of social media’s added value in disasters. Three years ago, it was the turn of ivory tower academics in the social sciences to dismiss the value added of social media for disaster response. The criticisms focused on the notion that reports posted on social media were simply untrustworthy and hardly representative. The above peer-reviewed scientific study dismisses these limitations as inconsequential.

Screen Shot 2016-03-17 at 1.11.17 PM

Establishing Social Media Hashtag Standards for Disaster Response

The UN Office for the Coordination of Humanitarian Affairs (OCHA) has just published an important, must-read report on the use of social media for disaster response. As noted by OCHA, this document was inspired by conversations with my team and I at QCRI. We jointly recognize that innovation in humanitarian technology is not enough. What is needed—and often lacking—is innovation in policymaking. Only then can humanitarian technology have widespread impact. This new think piece by OCHA seeks to catalyze enlightened policymaking.

ebolatags

I was pleased to provide feedback on earlier drafts of this new study and look forward to discussing the report’s recommendations with policymakers across the humanitarian space. In the meantime, many thanks to Roxanne Moore and Andrej Verity for making this report a reality. As Andrej notes in his blog post on this new study, the Filipino Government has just announced that “twitter will become another source of information for the Philippines official emergency response mechanism,” which will lead to an even more pressing Big (Crisis) Data challenge. The use of standardized hashtags will thus be essential.

hashtags-cartoon

The overflow of information generated during disasters can be as paralyzing to disaster response as the absence of information. While information scarcity has long characterized our information landscapes, today’s information-scapes are increasingly marked by an overflow of information—Big Data. To this end, encouraging the proactive standardization of hashtags may be one way to reduce this Big Data challenge. Indeed, standardized hashtags—i.e., more structured information—would enable paid emergency responders (as well as affected communities) to “better leverage crowdsourced information for operational planning and response.” At present, the Government of the Philippines seems to be the few actors that actually endorse the use of specific hashtags during major disasters as evidenced by their official crisis hashtags strategy.

The OCHA report thus proposes three hashtag standards and also encourages social media users to geo-tag their content during disasters. The latter can be done by enabling auto-GPS tagging or by using What3Words. Users should of course be informed of data-privacy considerations when geo-tagging their reports. As for the three hashtag standards:

  1. Early standardization of hashtags designating a specific disaster
  2. Standard, non-changing hashtag for reporting non-emergency needs
  3. Standard, non-changing hashtags for reporting emergency needs

1. As the OCHA think piece rightly notes, “News stations have been remarkably successful in encouraging early standardization of hashtags, especially during political events.” OCHA thus proposes that humanitarian organizations take a “similar approach for emergency response reporting and develop partnerships with Twitter as well as weather and news teams to publicly encourage such standardization. Storm cycles that create hurricanes and cyclones are named prior to the storm. For these events, an official hashtag should be released at the same time as the storm announcement.” For other hazards, “emergency response agencies should monitor the popular hashtag identifying a disaster, while trying to encourage a standard name.”

2. OCHA advocates for the use of #iSee, #iReport or #PublicRep for members of the public to designate tweets that refer to non-emergency needs such as “power lines, road closures, destroyed bridges, large-scale housing damage, population displacement or geographic spread (e.g., fire or flood).” When these hashtags are accompanied with GPS information, “responders can more easily identify and verify the information, therefore supporting more timely response & facilitating recovery.” In addition, responders can more easily create live crisis maps on the fly thanks to this structured, geo-tagged information.

3. As for standard hashtags for emergency reports, OCHA notes emergency calls are starting to give way to emergency SMS’s. Indeed, “Cell phone users will soon be able to send an SMS to a toll-free phone number. For emergency reporting, this new technology could dramatically alter the way the public interacts with nation-based emergency response call centers. It does not take a large imaginary leap to see the potential move from SMS emergency calls to social media emergency calls. Hashtags could be one way to begin reporting emergencies through social media.”

Most if not all countries have national emergency phone numbers already. So OCHA suggests using these existing, well-known numbers as the basis for social media hashtags. More specifically, an emergency hashtag would be composed of the country’s emergency number (such as 911 in the US, 999 in the UK, 133 in Austria, etc) followed by the country’s two-letter code (US, UK, AT respectively). In other words: #911US, #999UK, #133AT. Some countries, like Austria, have different emergency phone numbers for different types of emergencies. So these could also be used accordingly. OCHA recognizes that many “federal agencies fear that such a system would result in people reporting through social media outside of designated monitoring times. This is a valid concern. However, as with the implementation of any new technology in the public service, it will take time and extensive promotion to ensure effective use.”

Digital Humanitarians: The Book

Of course, “no monitoring system will be perfect in terms of low-cost, real-time analysis and high accuracy.” OCHA knows very well that there are a number of important limitations to the system they propose above. To be sure, “significant steps need to be taken to ensure that information flows from the public to response agencies and back to the public through improved efforts.” This is an important theme in my forthcoming book “Digital Humanitarians.”

bio

See also:

  • Social Media & Emergency Management: Supply and Demand [link]
  • Using AIDR to Automatically Classify Disaster Tweets [link]

Quantifying Information Flow During Emergencies

I was particularly pleased to see this study appear in the top-tier journal, Nature. (Thanks to my colleague Sarah Vieweg for flagging). Earlier studies have shown that “human communications are both temporally & spatially localized following the onset of emergencies, indicating that social propagation is a primary means to propagate situational awareness.” In this new study, the authors analyze crisis events using country-wide mobile phone data. To this end, they also analyze the communication patterns of mobile phone users outside the affected area. So the question driving this study is this: how do the communication patterns of non-affected mobile phone users differ from those affected? Why ask this question? Understanding the communication patterns of mobile phone users outside the affected areas sheds light on how situational awareness spreads during disasters.

Nature graphs

The graphs above (click to enlarge) simply depict the change in call volume for three crisis events and one non-emergency event for the two types of mobile phone users. The set of users directly affected by a crisis is labeled G0 while users they contact during the emergency are labeled G1. Note that G1 users are not affected by the crisis. Since the study seeks to assess how G1 users change their communication patterns following a crisis, one logical question is this: do the call volume of G1 users increase like those of G0 users? The graphs above reveal that G1 and G0 users have instantaneous and corresponding spikes for crisis events. This is not the case for the non-emergency event.

“As the activity spikes for G0 users for emergency events are both temporally and spatially localized, the communication of G1 users becomes the most important means of spreading situational awareness.” To quantify the reach of situational awareness, the authors study the communication patterns of G1 users after they receive a call or SMS from the affected set of G0 users. They find 3 types of communication patterns for G1 users, as depicted below (click to enlarge).

Nature graphs 2

Pattern 1: G1 users call back G0 users (orange edges). Pattern 2: G1 users call forward to G2 users (purple edges). Pattern 3: G1 users call other G1 users (green edges). Which of these 3 patterns is most pronounced during a crisis? Pattern 1, call backs, constitute 25% of all G1 communication responses. Pattern 2, call forwards, constitutes 70% of communications. Pattern 3, calls between G1 users only represents 5% of all communications. This means that the spikes in call volumes shown in the above graphs is overwhelmingly driven by Patterns 1 and 2: call backs and call forwards.

The graphs below (click to enlarge) show call volumes by communication patterns 1 and 2. In these graphs, Pattern 1 is the orange line and Pattern 2 the dashed purple line. In all three crisis events, Pattern 1 (call backs) has clear volume spikes. “That is, G1 users prefer to interact back with G0 users rather than contacting with new users (G2), a phenomenon that limits the spreading of information.” In effect, Pattern 1 is a measure of reciprocal communications and indeed social capital, “representing correspondence and coordination calls between social neighbors.” In contrast, Pattern 2 measures the dissemination of the “dissemination of situational awareness, corresponding to information cascades that penetrate the underlying social network.”

Nature graphs 3

The histogram below shows average levels of reciprocal communication for the 4 events under study. These results clearly show a spike in reciprocal behavior for the three crisis events compared to the baseline. The opposite is true for the non-emergency event.Nature graphs 4

In sum, a crisis early warning system based on communication patterns should seek to monitor changes in the following two indicators: (1) Volume of Call Backs; and (2) Deviation of Call Backs from baseline. Given that access to mobile phone data is near-impossible for the vast majority of academics and humanitarian professionals, one question worth exploring is whether similar communication dynamics can be observed on social networks like Twitter and Facebook.

 bio

Using Social Media to Predict Disaster Resilience (Updated)

Social media is used to monitor and predict all kinds of social, economic, political and health-related behaviors these days. Could social media also help identify more disaster resilient communities? Recent empirical research reveals that social capital is the most important driver of disaster resilience; more so than economic and material resources. To this end, might a community’s social media footprint indicate how resilience it is to disasters? After all, “when extreme events at the scale of Hurricane Sandy happen, they leave an unquestionable mark on social media activity” (1). Could that mark be one of resilience?

Twitter Heatmap Hurricane

Sentiment analysis map of tweets posted during Hurricane Sandy.
Click on image to learn more.

In the immediate aftermath of a disaster, “social ties can serve as informal insurance, providing victims with information, financial help and physical assistance” (2). This informal insurance, “or mutual assistance involves friends and neighbors providing each other with information, tools, living space, and other help” (3). At the same time, social media platforms like Twitter are increasingly used to communicate during crises. In fact, data driven research on tweets posted during disasters reveal that many tweets provide victims with information, help, tools, living space, assistance and other more. Recent studies argue that “such interactions are not necessarily of inferior quality compared to simultaneous, face-to-face interactions” (4). What’s more, “In addition to the preservation and possible improvement of existing ties, interaction through social media can foster the creation of new relations” (5). Meanwhile, and “contrary to prevailing assumptions, there is evidence that the boom in social media that connects users globally may have simultaneously increased local connections” (6).

A recent study of 5 billion tweets found that Japan, Canada, Indonesia and South Korea have highest percentage of reciprocity on Twitter (6). This is important because “Network reciprocity tells us about the degree of cohesion, trust and social capital in sociology” (7). In terms of network density, “the highest values correspond to South Korea, Netherlands and Australia.” The findings further reveal that “communities which tend to be less hierarchical and more reciprocal, also displays happier language in their content updates. In this sense countries with high conversation levels … display higher levels of happiness too” (8).

A related study found that the language used in tweets can be used to predict the subjective well-being of those users (9). The same analysis revealed that the level of happiness expressed by Twitter users in a community are correlated with members of that same community who are not on social media. Data-driven studies on happiness also show that social bonds and social activities are more conducive to happiness than financial capital (10). Social media also includes blogs. A new study analyzed more than 18.5 million blog posts found that “bloggers with lower social capital have fewer positive moods and more negative moods [as revealed by their posts] than those with higher social capital” (11).

Collectivism vs Individualism countries

Finally, another recent study analyzed more than 2.3 million twitter users and found that users in collectivist countries engage with others more than those in individualistic countries (12). “In high collectivist cultures, users tend to focus more on the community to which they belong,” while  people in individualistic countries are “in a more loosely knit social network,” and so typically “look after themselves or only after immediate family members” (13). The map above displays collectivist and individualistic countries; with the former represented by lighter shades and the latter darker colors.

In sum, one should be able to measure “digital social capital” and thus disaster resilience by analyzing social media networks before, during and after disasters. “These disaster responses may determine survival, and we can measure the likelihood of them happening” via digital social capital dynamics reflected on social media (14). One could also combine social network analysis with sentiment analysis to formulate various indexes. Anyone interested in pursuing this line of research?

bio

Analyzing Crisis Hashtags on Twitter (Updated)

Update: You can now upload your own tweets to the Crisis Hashtags Analysis Dashboard here

Hashtag footprints can be revealing. The map below, for example, displays the top 200 locations in the world with the most Twitter hashtags. The top 5 are Sao Paolo, London, Jakarta, Los Angeles and New York.

Hashtag map

A recent study (PDF) of 2 billion geo-tagged tweets and 27 million unique hashtags found that “hashtags are essentially a local phenomenon with long-tailed life spans.” The analysis also revealed that hashtags triggered by external events like disasters “spread faster than hashtags that originate purely within the Twitter network itself.” Like other metadata, hashtags can be  informative in and of themselves. For example, they can provide early warning signals of social tensions in Egypt, as demonstrated in this study. So might they also reveal interesting patterns during and after major disasters?

Tens of thousands of distinct crisis hashtags were posted to Twitter during Hurricane Sandy. While #Sandy and #hurricane featured most, thousands more were also used. For example: #SandyHelp, #rallyrelief, #NJgas, #NJopen, #NJpower, #staysafe, #sandypets, #restoretheshore, #noschool, #fail, etc. NJpower, for example, “helped keep track of the power situation throughout the state. Users and news outlets used this hashtag to inform residents where power outages were reported and gave areas updates as to when they could expect their power to come back” (1).

Sandy Hashtags

My colleagues and I at QCRI are studying crisis hashtags to better understand the variety of tags used during and in the immediate aftermath of major crises. Popular hashtags used during disasters often overshadow more hyperlocal ones making these less discoverable. Other challenges include the: “proliferation of hashtags that do not cross-pollinate and a lack of usability in the tools necessary for managing massive amounts of streaming information for participants who needed it” (2). To address these challenges and analyze crisis hashtags, we’ve just launched a Crisis Hashtags Analytics Dashboard. As displayed below, our first case study is Hurricane Sandy. We’ve uploaded about half-a-million tweets posted between October 27th to November 7th, 2012 to the dashboard.

QCRI_Dashboard

Users can visualize the frequency of tweets (orange line) and hashtags (green line) over time using different time-steps, ranging from 10 minute to 1 day intervals. They can also “zoom in” to capture more minute changes in the number of hashtags per time interval. (The dramatic drop on October 30th is due to a server crash. So if you have access to tweets posted during those hours, I’d be  grateful if you could share them with us).

Hashtag timeline

In the second part of the dashboard (displayed below), users can select any point on the graph to display the top “K” most frequent hashtags. The default value for K is 10 (e.g., top-10 most frequent hashtags) but users can change this by typing in a different number. In addition, the 10 least-frequent hashtags are displayed, as are the 10 “middle-most” hashtags. The top-10 newest hashtags posted during the selected time are also displayed as are the hashtags that have seen the largest increase in frequency. These latter two metrics, “New K” and “Top Increasing K”, may provide early warning signals during disasters. Indeed, the appearance of a new hashtag can reveal a new problem or need while a rapid increase in the frequency of some hashtags can denote the spread of a problem or need.

QCRI Dashboard 2

The third part of the dashboard allows users to visualize and compare the frequency of top hashtags over time. This feature is displayed in the screenshot below. Patterns that arise from diverging or converging hashtags may indicate important developments on the ground.

QCRI Dashboard 3

We’re only at the early stages of developing our hashtags analytics platform (above), but we hope the tool will provide insights during future disasters. For now, we’re simply experimenting and tinkering. So feel free to get in touch if you would like to collaborate and/or suggest some research questions.

Bio

Acknowledgements: Many thanks to QCRI colleagues Ahmed Meheina and Sofiane Abbar for their work on developing the dashboard.

Social Network Analysis for Digital Humanitarian Response

Monitoring social media for digital humanitarian response can be a massive undertaking. The sheer volume and velocity of tweets generated during a disaster makes real-time social media monitoring particularly challenging if not near impossible. However, two new studies argue that there is “a better way to track the spread of information on Twitter that is much more powerful.”

Twitter-Hadoop31

Manuel Garcia-Herranz and his team at the Autonomous University of Madrid in Spain use small groups of “highly connected Twitter users as ‘sensors’ to detect the emergence of new ideas. They point out that this works because highly co-nnected individuals are more likely to receive new ideas before ordinary users.” The test their hypothesis, the team studied 40 million Twitters users who “together totted up 1.5 billion follows’ and sent nearly half a billion tweets, including 67 million containing hashtags.”

They found that small groups of highly connected Twitter users detect “new hashtags about seven days earlier than the control group.  In fact, the lead time varied between nothing at all and as much as 20 days.” Manuel and his team thus argue that “there’s no point in crunching these huge data sets. You’re far better off picking a decent sensor group and watching them instead.” In other words, “your friends could act as an early warning system, not just for gossip, but for civil unrest and even outbreaks of disease.”

The second study, “Identifying and Characterizing User Communities on Twitter during Crisis Events,” (PDF) is authored by Aditi Gupta et al. Aditi and her co-lleagues analyzed three major crisis events (Hurricane Irene, Riots in England and Earthquake in Virginia) to “to identify the different user communities, and characterize them by the top central users.” Their findings are in line with those shared by the team in Madrid. “[T]he top users represent the topics and opinions of all the users in the community with 81% accuracy on an average.” In sum, “to understand a community, we need to monitor and analyze only these top users rather than all the users in a community.”

How could these findings be used to prioritize the monitoring of social media during disasters? See this blog post for more on the use of social network analysis (SNA) for humanitarian response.