Category Archives: Social Computing

Social Media Generates Social Capital: Implications for City Resilience and Disaster Response

A new empirical and peer-reviewed study provides “the first evidence that online networks are able to produce social capital. In the case of bonding social capital, online ties are more effective in forming close networks than theory predicts.” Entitled, “Tweeting Alone? An Analysis of Bridging and Bonding Social Capital in Online Networks,” the study analyzes Twitter data generated during three large events: “the Occupy movement in 2011, the IF Campaign in 2013, and the Chilean Presidential Election of the same year.”

cityres

What is the relationship between social media and social capital formation? More specifically, how do connections established via social media—in this case Twitter—lead to the formation of two specific forms of social capital, bridging and bonding capital? Does the interplay between bridging and bonding capital online differ to what we see in face-to-face world interactions?

“Bonding social capital exists in the strong ties occurring within, often homogeneous, groups—families, friendship circles, work teams, choirs, criminal gangs, and bowling clubs, for example. Bonding social capital acts as a social glue, building trust and norms within groups, but also potentially increasing intolerance and distrust of out-group members. Bridging social capital exists in the ties that link otherwise separate, often heterogeneous, groups—so for example, individuals with ties to other groups, messengers, or more generically the notion of brokers. Bridging social capital allows different groups to share and exchange information, resources, and help coordinate action across diverse interests.” The authors emphasize that “these are not either/or categories, but that in well-functioning societies the two types or dimensions develop together.”

The study uses social network analysis to measure bonding and bridging social capital. More specifically, they use two associated metrics as indicators of social capital: closure and brokerage. “Closure refers to the level of connectedness between particular groups of members within a broader network and encourages the formation of trust and collaboration. Brokerage refers to the existence of structural holes within a network that are ’bridged’ by a particular member of the network. Brokerage permits the transmission of information across the entire network. Social capital, then, is comprised of the combination of these two elements, which interact over time.”

The authors thus analyze the “observed values for closure and brokerage over time and compare them with different simulations based on theoretical network models to show how they compare to what we would expect offline. From this, [they provide an evaluation of the existence and formation of social capital in online networks.”

The results demonstrate that “online networks show evidence of social capital and these networks exhibit higher levels of closure than what would be expected based on theoretical models. However, the presence of organizations and professional brokers is key to the formation of bridging social capital. Similar to traditional (offline) conditions, bridging social capital in online networks does not exist organically and requires the purposive efforts of network members to connect across different groups. Finally, the data show interaction between closure and brokerage goes in the right direction, moving and growing together.”

These conclusions suggest that the same metrics—closure and brokerage—can be used to monitor “City Resilience” before, during and after major disasters. This is of particular interest to me since my team and I at QCRI are collaborating with the Rockefeller Foundation’s 100 Resilient Cities initiative to determine whether social media can indeed help monitor (proxy indicators of) resilience. Recent studies have shown that changes in employment, economic activity and mobility—each of which is are drivers of resilience—can be gleamed from social media.

While more research is needed, the above findings are compelling enough for us to move forward with Rockefeller on our joint project. So we’ll be launching AIRS in early 2015. AIRS, which stands for “Artificial Intelligence for Resilient Societies” is a free and open source platform specifically designed to enable Rockefeller’s partners cities to monitor proxy indicators of resilience on Twitter.

Bio

See also:

  • Using Social Media to Predict Disaster Resilience [link]
  • Social Media = Social Capital = Disaster Resilience? [link]
  • Does Social Capital Drive Disaster Resilience? [link]
  • Digital Social Capital Matters for Resilience & Response [link]

Using Social Media to Anticipate Human Mobility and Resilience During Disasters

The analysis of cell phone data can already be used to predict mobility patterns after major natural disasters. Now, a new peer-reviewed scientific study suggests that travel patterns may also be predictable using tweets generated following large disasters. In “Quantifying Human Mobility Perturbation and Resilience in Hurricane Sandy,” co-authors Qi Wang and John Taylor analyze some 700,000 geo-tagged tweets posted by ~53,000 individuals as they moved around over the course of 12 days. Results of the analysis confirm that “Sandy did impact the mobility patterns of individuals in New York City,” but this “perturbation was surprisingly brief and the mobility patterns encouragingly resilient. This resilience occurred even in the large-scale absence of mobility infrastructure.”

Twitter Mobility

In sum, this new study suggests that “Human mobility appears to possess an inherent resilience—even in perturbed states—such that movement deviations, in aggregate, follow predictable patterns in hurricanes. Therefore, it may be possible to use human mobility data collected in steady states to predict perturbation states during extreme events and, as a result, develop strategies to improve evacuation effectiveness & speed critical disaster response to minimize loss of life and human suffering.”

Authors Wang and Taylor are now turning their attention to “10 other storms and typhoons that they’ve collected data on.” They hope to further demonstrate that quantifying mobility patterns before and after disasters will eventually help cities “predict mobility in the face of a future disaster, and thereby protect and serve residents better.” They also want to “understand where the ‘upper limit’ of resilience lies. ‘After Haiyan,’—the deadliest-ever Philippine Typhoon that struck last November—’there was a total breakdown in mobility patterns,’ says Taylor.”

Of course, Twitter data comes with well-known limitations such as demographic bias, for example. This explains why said data must be interpreted carefully and why the results simply augment rather than replace the analysis of traditional data sources used for damage after needs assessments after disasters.

bio

See also:

  • Social Media & Emergency Management: Supply and Demand [link]
  • Using AIDR to Automatically Classify Disaster Tweets [link]
  • Visualization of Photos Posted to Instagram During Sandy [link]
  • Using Twitter to Map Blackouts During Hurricane Sandy [link]
  • Analyzing Foursquare Check-Ins During Hurricane Sandy [link]

Digital Jedis: There Has Been An Awakening…

Computing Research Institutes as an Innovation Pathway for Humanitarian Technology

The World Humanitarian Summit (WHS) is an initiative by United Nations Secretary-General Ban Ki-moon to improve humanitarian action. The Summit, which is to be held in 2016, stands to be one of the most important humanitarian conferences in a decade. One key pillar of WHS is humanitarian innovation. “Transformation through Innovation” is the WHS Working Group dedicated to transforming humanitarian action by focusing explicitly on innovation. I have the pleasure of being a member of this working group where my contribution focuses on the role of new technologies, data science and advanced computing. As such, I’m working on an applied study to explore the role of computing research institutes as an innovation pathway for humanitarian technology. The purpose of this blog post is to invite feedback on the ideas presented below.

WHS_Logo_0

I first realized that the humanitarian community faced a “Big Data” challenge in 2010, just months after I had joined Ushahidi as Director of Crisis Mapping, and just months after co-founding CrisisMappers: The Humanitarian Technology Network. The devastating Haiti Earthquake resulted in a massive overflow of information generated via mainstream news, social media, text messages and satellite imagery. I launched and spearheaded the Haiti Crisis Map at the time and together with hundreds of digital volunteers from all around the world went head-to head with Big Data. As noted in my forthcoming book, we realized there and then that crowdsourcing and mapping software alone were no match for Big (Crisis) Data.

Digital Humanitarians: The Book

This explains why I decided to join an advanced computing research institute, namely QCRI. It was clear to me after Haiti that humanitarian organizations had to partner directly with advanced computing experts to manage the new Big Data challenge in disaster response. So I “embedded” myself in an institute with leading experts in Big Data Analytics, Data Science and Social Computing. I believe that computing research institutes (CRI’s) can & must play an important role in fostering innovation in next generation humanitarian technology by partnering with humanitarian organizations on research & development (R&D).

There is already some evidence to support this proposition. We (QCRI) teamed up with the UN Office for the Coordination of Humanitarian Affairs (OCHA) to create the Artificial Intelligence for Disaster Response platform, AIDR as well as MicroMappers. We are now extending AIDR to analyze text messages (SMS) in partnership with UNICEF. We are also spearheading efforts around the use and analysis of aerial imagery (captured via UAVs) for disaster response (see the Humanitarian UAV Network: UAViators). On the subject of UAVs, I believe that this new technology presents us (in the WHS Innovation team) with an ideal opportunity to analyze in “real time” how a new, disruptive technology gets adopted within the humanitarian system. In addition to UAVs, we catalyzed a partnership with Planet Labs and teamed up with Zooniverse to take satellite imagery analysis to the next level with large scale crowd computing. To this end, we are working with humanitarian organizations to enable them to make sense of Big Data generated via social media, SMS, aerial imagery & satellite imagery.

The incentives for humanitarian organizations to collaborate with CRI’s are obvious, especially if the latter (like QCRI) commits to making the resulting prototypes freely accessible and open source. But why should CRI’s collaborate with humanitarian organizations in the first place? Because the latter come with real-world challenges and unique research questions that many computer scientists are very interested in for several reasons. First, carrying out scientific research on real-world problems is of interest to the vast majority of computer scientists I collaborate with, both within QCRI and beyond. These scientists want to apply their skills to make the world a better place. Second, the research questions that humanitarian organizations bring enable computer scientists to differentiate themselves in the publishing world. Third, the resulting research can help advanced the field of computer science and advanced computing.

So why are we see not seeing more collaboration between CRI’s & humanitarian organizations? Because of this cognitive surplus mismatch. It takes a Director of Social Innovation (or related full-time position) to serve as a translational leader between CRI’s and humanitarian organizations. It takes someone (ideally a team) to match the problem owners and problem solvers; to facilitate and manage the collaboration between these two very different types of expertise and organizations. In sum, CRI’s can serve as an innovation pathway if the following three ingredients are in place: 1) Translation Leader; 2) Committed CRI; and 3) Committed Humanitarian Organization. These are necessary but not sufficient conditions for success.

While research institutes have a comparative advantage in R&D, they are not the best place to scale humanitarian technology prototypes. In order to take these prototypes to the next level, make them sustainable and have them develop into enterprise level software, they need to be taken up by for-profit companies. The majority of CRI’s (QCRI included) actually do have a mandate to incubate start-up companies. As such, we plan to spin-off some of the above platforms as independent companies in order to scale the technologies in a robust manner. Note that the software will remain free to use for humanitarian applications; other uses of the platform will require a paid license. Therein lies the end-to-end innovation path that computing research institutes can offer humanitarian organization vis-a-vis next generation humanitarian technologies.

As noted above, part of my involvement with the WHS Innovation Team entails working on an applied study to document and replicate this innovation pathway. As such, I am looking for feedback on the above as well as on the research methodology described below.

I plan to interview Microsoft Research, IBM Research, Yahoo Research, QCRI and other institutes as part of this research. More specifically, the interview questions will include:

  • Have you already partnered with humanitarian organizations? Why/why not?
  • If you have partnered with humanitarian organizations, what was the outcome? What were the biggest challenges? Was the partnership successful? If so, why? If not, why not?
  • If you have not yet partnered with humanitarian organizations, why not? What factors would be conducive to such partnerships and what factors serve as hurdles?
  • What are your biggest concerns vis-a-vis working with humanitarian groups?
  • What funding models did you explore if any?

I also plan to interview humanitarian organizations to better understand the prospects for this potential innovation pathway. More specifically, I plan to interview ICRC, UNHCR, UNICEF and OCHA using the following questions:

  • Have you already partnered with computing research groups? Why/why not?
  • If you have partnered with computing research groups, what was the outcome? What were the biggest challenges? Was the partnership successful? If so, why? If not, why not?
  • If you have not yet partnered with computing research groups, why not? What factors would be conducive to such partnerships and what factors serve as hurdles?
  • What are your biggest concerns vis-a-vis working with computing research groups?
  • What funding models did you explore if any?

My plan is to carry out the above semi-structured interviews in February-March 2015 along with secondary research. My ultimate aim with this deliverable is to develop a model to facilitate greater collaboration between computing research institutes and humanitarian organizations. To this end, I welcome feedback on all of the above (feel free to email me and/or add comments below). Thank you.

Bio

See also:

  • Research Framework for Next Generation Humanitarian Technology and Innovation [link]
  • From Gunfire at Sea to Maps of War: Implications for Humanitarian Innovation [link]

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]

Using Flash Crowds to Automatically Detect Earthquakes & Impact Before Anyone Else

It is said that our planet has a new nervous system; a digital nervous system comprised of digital veins and intertwined sensors that capture the pulse of our planet in near real-time. Next generation humanitarian technologies seek to leverage this new nervous system to detect and diagnose the impact of disasters within minutes rather than hours. To this end, LastQuake may be one of the most impressive humanitarian technologies that I have recently come across. Spearheaded by the European-Mediterranean Seismological Center (EMSC), the technology combines “Flashsourcing” with social media monitoring to auto-detect earthquakes before they’re picked up by seismometers or anyone else.

Screen Shot 2014-10-23 at 5.08.30 PM

Scientists typically draw on ground-motion prediction algorithms and data on building infrastructure to rapidly assess an earthquake’s potential impact. Alas, ground-motion predictions vary significantly and infrastructure data are rarely available at sufficient resolutions to accurately assess the impact of earthquakes. Moreover, a minimum of three seismometers are needed to calibrate a quake and said seismic data take several minutes to generate. This explains why the EMSC uses human sensors to rapidly collect relevant data on earthquakes as these reduce the uncertainties that come with traditional rapid impact assess-ment methodologies. Indeed, the Center’s important work clearly demonstrates how the Internet coupled with social media are “creating new potential for rapid and massive public involvement by both active and passive means” vis-a-vis earthquake detection and impact assessments. Indeed, the EMSC can automatically detect new quakes within 80-90 seconds of their occurrence while simultaneously publishing tweets with preliminary information on said quakes, like this one:

Screen Shot 2014-10-23 at 5.44.27 PM

In reality, the first human sensors (increases in web traffic) can be detected within 15 seconds (!) of a quake. The EMSC’s system continues to auto-matically tweet relevant information (including documents, photos, videos, etc.), for the first 90 minutes after it first detects an earthquake and is also able to automatically create a customized and relevant hashtag for individual quakes.

Screen Shot 2014-10-23 at 5.51.05 PM

How do they do this? Well, the team draw on two real-time crowdsourcing methods that “indirectly collect information from eyewitnesses on earthquakes’ effects.” The first is TED, which stands for Twitter Earthquake Detection–a system developed by the US Geological Survey (USGS). TED filters tweets by key word, location and time to “rapidly detect sharing events through increases in the number of tweets” related to an earthquake. The second method, called “flashsourcing” was developed by the European-Mediterranean to analyze traffic patterns on its own website, “a popular rapid earthquake information website.” The site gets an average of 1.5 to 2 million visits a month. Flashsourcing allows the Center to detect surges in web traffic that often occur after earthquakes—a detection method named Internet Earthquake Detection (IED). These traffic surges (“flash crowds”) are caused by “eyewitnesses converging on its website to find out the cause of their shaking experience” and can be detected by analyzing the IP locations of website visitors.

It is worth emphasizing that both TED and IED work independently from traditional seismic monitoring systems. Instead, they are “based on real-time statistical analysis of Internet-based information generated by the reaction of the public to the shaking.” As EMSC rightly notes in a forthcoming peer-reviewed scientific study, “Detections of felt earthquakes are typically within 2 minutes for both methods, i.e., considerably faster than seismographic detections in poorly instrumented regions of the world.” TED and IED are highly complementary methods since they are based on two entirely “different types of Internet use that might occur after an earthquake.” TED depends on the popularity of Twitter while IED’s effectiveness depends on how well known the EMSC website is in the area affected by an earthquake. LastQuake automatically publishes real-time information on earthquakes by automatically merging real-time data feeds from both TED and IED as well as non-crowdsourcing feeds.

infographie-CSEM-LastQuake2

Lets looks into the methodology that powers IED. Flashsourcing can be used to detect felt earthquakes and provide “rapid information (within 5 minutes) on the local effects of earthquakes. More precisely, it can automatically map the area where shaking was felt by plotting the geographical locations of statistically significant increases in traffic […].” In addition, flashsourcing can also “discriminate localities affected by alarming shaking levels […], and in some cases it can detect and map areas affected by severe damage or network disruption through the concomitant loss of Internet sessions originating from the impacted region.” As such, this “negative space” (where there are no signals) is itself an important signal for damage assessment, as I’ve argued before.

remypicIn the future, EMSC’s flashsourcing system may also be able discriminate power cuts between indoor and outdoor Internet connections at the city level since the system’s analysis of web traffic session will soon be based on web sockets rather than webserver log files. This automatic detection of power failures “is the first step towards a new system capable of detecting Internet interruptions or localized infrastructure damage.” Of course, flashsourcing alone does not “provide a full description of earthquake impact, but within a few minutes, independently of any seismic data, and, at little cost, it can exclude a number of possible damage scenarios, identify localities where no significant damage has occurred and others where damage cannot be excluded.”

Screen Shot 2014-10-23 at 5.59.20 PM

EMSC is complementing their flashsourching methodology with a novel mobile app that quickly enables smartphone users to report about felt earthquakes. Instead of requiring any data entry and written surveys, users simply click on cartoonish-type pictures that best describe the level of intensity they felt when the earthquake (or aftershocks) struck. In addition, EMSC analyzes and manually validates geo-located photos and videos of earthquake effects uploaded to their website (not from social media). The Center’s new app will also make it easier for users to post more pictures more quickly.

CSEM-tweets2

What about typical criticisms (by now broken records) that social media is biased and unreliable (and thus useless)? What about the usual theatrics about the digital divide invalidating any kind of crowdsourcing effort given that these will be heavily biased and hardly representative of the overall population? Despite these already well known short-comings and despite the fact that our inchoate digital networks are still evolving into a new nervous system for our planet, the existing nervous system—however imperfect and immature—still adds value. TED and LastQuake demonstrate this empirically beyond any shadow of a doubt. What’s more, the EMSC have found that crowdsourced, user-generated information is highly reliable: “there are very few examples of intentional misuses, errors […].”

My team and I at QCRI are honored to be collaborating with EMSC on integra-ting our AIDR platform to support their good work. AIDR enables uses to automatically detect tweets of interest by using machine learning (artificial intelligence) which is far more effective searching for keywords. I recently spoke with Rémy Bossu, one masterminds behind the EMSC’s LastQuake project about his team’s plans for AIDR:

“For us AIDR could be a way to detect indirect effects of earthquakes, and notably triggered landslides and fires. Landslides can be the main cause of earthquake losses, like during the 2001 Salvador earthquake. But they are very difficult to anticipate, depending among other parameters on the recent rainfalls. One can prepare a susceptibility map but whether there are or nor landslides, where they have struck and their extend is something we cannot detect using geophysical methods. For us AIDR is a tool which could potentially make a difference on this issue of rapid detection of indirect earthquake effects for better situation awareness.”

In other words, as soon as the EMSC system detects an earthquake, the plan is for that detection to automatically launch an AIDR deployment to automatically identify tweets related to landslides. This integration is already completed and being piloted. In sum, EMSC is connecting an impressive ecosystem of smart, digital technologies powered by a variety of methodologies. This explains why their system is one of the most impressive & proven examples of next generation humanitarian technologies that I’ve come across in recent months.

bio

Acknowledgements: Many thanks to Rémy Bossu for providing me with all the material and graphics I needed to write up this blog post.

See also:

  • Social Media: Pulse of the Planet? [link]
  • Taking Pulse of Boston Bombings [link]
  • The World at Night Through the Eyes of the Crowd [link]
  • The Geography of Twitter: Mapping the Global Heartbeat [link]

Integrating Geo-Data with Social Media Improves Situational Awareness During Disasters

A new data-driven study on the flooding of River Elbe in 2013 (one of the most severe floods ever recorded in Germany) shows that geo-data can enhance the process of extracting relevant information from social media during disasters. The authors use “specific geographical features like hydrological data and digital elevation models to prioritize crisis-relevant twitter messages.” The results demonstrate that an “approach based on geographical relations can enhance information extraction from volunteered geographic information,” which is “valuable for both crisis response and preventive flood monitoring.” These conclusions thus support a number of earlier studies that show the added value of data integration. This analysis also confirms several other key assumptions, which are important for crisis computing and disaster response.

floods elbe

The authors apply a “geographical approach to prioritize [the collection of] crisis-relevant information from social media.” More specifically, they combine information from “tweets, water level measurements & digital elevation models” to answer the following three research questions:

  • Does the spatial and temporal distribution of flood-related tweets actually match the spatial and temporal distribution of the flood phenomenon (despite Twitter bias, potentially false info, etc)?

  • Does the spatial distribution of flood-related tweets differ depending on their content?
  • Is geographical proximity to flooding a useful parameter to prioritize social media messages in order to improve situation awareness?

The authors analyzed just over 60,000 disaster-related tweets generated in Germany during the flooding of River Elbe in June 2013. Only 398 of these tweets (0.7%) contained keywords related to the flooding. The geographical distribution of flood-related tweets versus non-flood related tweets is depicted below (click to enlarge).

Screen Shot 2014-10-04 at 7.04.59 AM

As the authors note, “a considerable amount” of flood-related tweets are geo-located in areas of major flooding. So they tested the statistical correlation between the location of flood-related tweets and the actual flooding, which they found to be “statistically significantly lower compared to non-related Twitter messages.” This finding “implies that the locations of flood-related twitter messages and flood-affected catchments match to a certain extent. In particular this means that mostly people in regions affected by the flooding or people close to these regions posted twitter messages referring to the flood.” To this end, major urban areas like Munich and Hamburg were not the source of most flood-related tweets. Instead, “The majority of tweet referring to the flooding were posted by locals” closer to the flooding.

Given that “most flood-related tweets were posted by locals it seems probable that these messages contain local knowledge only available to people on site.” To this end, the authors analyzed the “spatial distribution of flood-related tweets depending on their content.” The results, depicted below (click to enlarge), show that the geographical distribution of tweets do indeed differ based on their content. This is especially true of tweets containing information about “volunteer actions” and “flood level”. The authors confirm these results are statistically significant when compared with tweets related to “media” and “other” issues.

Screen Shot 2014-10-04 at 7.22.05 AM

These findings also reveal that the content of Twitter messages can be combined into three groups given their distance to actual flooding:

Group A: flood level & volunteer related tweets are closest to the floods.
Group B: tweets on traffic conditions have a medium distance to the floods.
Group C: other and media related tweets a furthest to the flooding.

Tweets belonging to “Group A” yield greater situational awareness. “Indeed, information about current flood levels is crucial for situation awareness and can complement existing water level measurements, which are only available for determined geographical points where gauging stations are located. Since volunteer actions are increasingly organized via social media, this is a type of information which is very valuable and completely missing from other sources.”

Screen Shot 2014-10-04 at 6.55.49 AM

In sum, these results show that “twitter messages that are closest to the flood- affected areas (Group A) are also the most useful ones.” The authors thus conclude that “the distance to flood phenomena is indeed a useful parameter to prioritize twitter messages towards improving situation awareness.” To be sure, the spatial distribution of flood-related tweets is “significantly different from the spatial distribution of off-topic messages.” Whether this is also true of other social media platforms like Instagram and Flickr remains to be seen. This is an important area for future research given the increasing use of pictures posted on social media for rapid damage assessments in the aftermath of disasters.

ImageClicker

“The integration of other official datasets, e.g. precipitation data or satellite images, is another avenue for future work towards better understanding the relations between social media and crisis phenomena from a geographical perspective.” I would add both aerial imagery (captured by UAVs) and data from mainstream news (captured by GDELT) to this data fusion exercise. Of course, the geographical approach described above is not limited to the study of flooding only but could be extended to other natural hazards.

This explains why my colleagues at GeoFeedia may be on the right track with their crisis mapping platform. That said, the main limitation with GeoFeedia and the study above is the fact that only 3% of all tweets are actually geo-referenced. But this need not be a deal breaker. Instead, platforms like GeoFeedia can be complemented by other crisis computing solutions that prioritize the analysis of social media content over geography.

Take the free and open-source “Artificial Intelligence for Disaster Response” (AIDR) platform that my team and I at QCRI are developing. Humanitarian organizations can use AIDR to automatically identify tweets related to flood levels and volunteer actions (deemed to provide the most situational awareness) without requiring that tweets be geo-referenced. In addition, AIDR can also be used to identify eyewitness tweets regardless of whether they refer to flood levels, volunteering or other issues. Indeed, we already demonstrated that eyewitness tweets can be automatically identified with an accuracy of 80-90% using AIDR. And note that AIDR can also be used on geo-tagged tweets only.

The authors of the above study recently go in touch to explore ways that their insights can be used to further improve AIDR. So stay tuned for future updates on how we may integrate geo-data more directly within AIDR to improve situational awareness during disasters.

bio

See also:

  • Debating the Value of Tweets For Disaster Response (Intelligently) [link]
  • Social Media for Emergency Management: Question of Supply and Demand [link]
  • Become a (Social Media) Data Donor and Save a Life [link]