From social networks to emergency operation centers: A semantic visualization approach

Abstract Social networks are commonly used by citizens as a communication channel for sharing their messages about a crisis situation and by emergency operation centers as a source of information for improving their situation awareness. However, to utilize this source of information, emergency operators and decision makers have to deal with large and unstructured data, the content, reliability, quality, and relevance of which may vary greatly. In this paper, to address this challenge, we propose a visual analytics solution that filters and visualizes relevant information extracted from Twitter. The tool offers multiple visualizations to provide emergency operators with different points of view for exploring the data in order to gain a better understanding of the situation and take informed courses of action. We analyzed the scope of the problem through an exploratory study in which 20 practitioners answered questions about the integration of social networks in the emergency management process. This study inspired the design of a visualization tool, which was evaluated in a controlled experiment to assess its effectiveness for exploring spatial and temporal data. During the experiment, we asked 12 participants to perform 5 tasks related to data exploration and fill a questionnaire about their experience using the tool. One of the most interesting results obtained from the evaluation concerns the effectiveness of combining several visualization techniques to support different strategies for solving a problem and making decisions.

[1]  David S. Ebert,et al.  Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition , 2012, 2012 IEEE Conference on Visual Analytics Science and Technology (VAST).

[2]  David E. Alexander,et al.  Social Media in Disaster Risk Reduction and Crisis Management , 2013, Science and Engineering Ethics.

[3]  Shaun Moon,et al.  Visual correlation for situational awareness , 2005, IEEE Symposium on Information Visualization, 2005. INFOVIS 2005..

[4]  E. L. Quarantelli,et al.  Emergent Citizen Groups and Emergency Management. , 1985 .

[5]  David S. Ebert,et al.  Applied visual analytics for economic decision-making , 2008, 2008 IEEE Symposium on Visual Analytics Science and Technology.

[6]  John M. Carroll,et al.  Coproduction as an Approach to Technology-Mediated Citizen Participation in Emergency Management , 2016, Future Internet.

[7]  Charlotte H. Mason,et al.  Visual Representation: Implications for Decision Making , 2007 .

[8]  Anthony C. Robinson,et al.  Geovisual Analytics and Crisis Management , 2007 .

[9]  R. Yin.  Case Study Research: Design and Methods , 1984 .

[10]  Volkmar Pipek,et al.  Crisis Management 2.0: Towards a Systematization of Social Software Use in Crisis Situations , 2012, Int. J. Inf. Syst. Crisis Response Manag..

[11]  M. Careem,et al.  Sahana: Overview of a Disaster Management System , 2006, 2006 International Conference on Information and Automation.

[12]  Thomas Ludwig,et al.  Strategy for processing and analyzing social media data streams in emergencies , 2015, 2015 2nd International Conference on Information and Communication Technologies for Disaster Management (ICT-DM).

[13]  Martin Wattenberg,et al.  TIMELINESTag clouds and the case for vernacular visualization , 2008, INTR.

[14]  Ronald L. Graham,et al.  An Efficient Algorithm for Determining the Convex Hull of a Finite Planar Set , 1972, Inf. Process. Lett..

[15]  Christopher D. Manning,et al.  Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger , 2000, EMNLP.

[16]  Philip Treleaven,et al.  Quantifying the Digital Traces of Hurricane Sandy on Flickr , 2013, Scientific Reports.

[17]  Ben Shneiderman,et al.  The eyes have it: a task by data type taxonomy for information visualizations , 1996, Proceedings 1996 IEEE Symposium on Visual Languages.

[18]  Ross Maciejewski,et al.  Understanding Twitter data with TweetXplorer , 2013, KDD.

[19]  B. Lindsay.  Social Media and Disasters: Current Uses, Future Options, and Policy Considerations , 2011 .

[20]  Ben Shneiderman,et al.  Tree visualization with tree-maps: 2-d space-filling approach , 1992, TOGS.

[21]  Starr Roxanne Hiltz,et al.  Online forums supporting grassroots participation in emergency preparedness and response , 2007, Commun. ACM.

[22]  Sophia B. Liu,et al.  Citizen communications in crisis: anticipating a future of ICT-supported public participation , 2007, CHI.

[23]  Paloma Díaz,et al.  Citizen Participation and Social Technologies: Exploring the Perspective of Emergency Organizations , 2014, ISCRAM-med.

[24]  Leysia Palen,et al.  Twitter adoption and use in mass convergence and emergency events , 2009 .

[25]  Yifan Hu,et al.  Interactive Visualization of Streaming Text Data with Dynamic Maps , 2013, J. Graph Algorithms Appl..

[26]  Ines Mergel,et al.  Social media adoption: toward a representative, responsive or interactive government? , 2014, DG.O.

[27]  Thomas Ludwig,et al.  Social Haystack , 2015, ACM Trans. Comput. Hum. Interact..

[28]  Martin Wattenberg,et al.  ManyEyes: a Site for Visualization at Internet Scale , 2007, IEEE Transactions on Visualization and Computer Graphics.

[29]  Thomas Ludwig,et al.  Emergency services' attitudes towards social media: A quantitative and qualitative survey across Europe , 2016, Int. J. Hum. Comput. Stud..

[30]  Paloma Díaz,et al.  Tweet Me and I'll Help You: Mapping Tweets for Emergency Operation Centers: The Case of Paris Attacks , 2016, 2016 International Conference on Collaboration Technologies and Systems (CTS).

[31]  Daniel A. Keim,et al.  Visual Analytics: Definition, Process, and Challenges , 2008, Information Visualization.

[32]  Paloma Díaz,et al.  Giving meaning to tweets in emergency situations: a semantic approach for filtering and visualizing social data , 2016, SpringerPlus.

[33]  Gennady L. Andrienko,et al.  Exploratory analysis of spatial and temporal data - a systematic approach , 2005 .