Using tweets to support disaster planning, warning and response

Abstract Twitter is increasingly of interest as a social media that can be used to help mitigate disasters. In this paper, we describe the strength and limitations of Twitter in this context, and identify the features needed in a twitter system to support disaster planning, warning and response. To orient the discussion, we describe a local context, Padang Indonesia. We then illustrate the kind of system needed by describing our implementation of TWRsms – a twitter tracking and analysis system for Padang Indonesia. Our implementation collects and analyzes tweets from the shoreline city of Padang Indonesia. This area is exposed to considerable risk from tsunamis, and the purpose of our system is to provide Indonesians information to plan for response to tsunamis, to provide immediate feedback about relevant tweeters in the wake of tsunami warnings, to support an early warning system, and to allow long-term research into how Indonesians tweet about disasters and other topics. We conclude by reviewing ongoing challenges: considering technical, social and policy issues and the challenge for science and the practical challenges of deploying such a system.

[1]  R. Basher.  Global early warning systems for natural hazards: systematic and people-centred , 2006, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[2]  Tony Waltham,et al.  The Asian Tsunami disaster, December 2004 , 2005 .

[3]  Axel Bruns,et al.  Tools and methods for capturing Twitter data during natural disasters , 2012, First Monday.

[4]  Adam Acar,et al.  Twitter for crisis communication: lessons learned from Japan's tsunami disaster , 2011, Int. J. Web Based Communities.

[5]  Robert Munro.  Crowdsourcing and the crisis-affected community , 2012, Information Retrieval.

[6]  Ayu Purwarianti,et al.  Sentiment classification for Indonesian message in social media , 2012, CLOUD 2012.

[7]  Taieb Znati,et al.  Design and implementation of a Witness Unit for opportunistic routing in tsunami alert scenarios , 2016 .

[8]  Kathleen M. Carley,et al.  Twitter Usage in Indonesia , 2015 .

[9]  Kathleen M. Carley.  ORA: A Toolkit for Dynamic Network Analysis and Visualization , 2014, Encyclopedia of Social Network Analysis and Mining.

[10]  Huan Liu,et al.  Embassies burning: toward a near-real-time assessment of social media using geo-temporal dynamic network analytics , 2014, Social Network Analysis and Mining.

[11]  L. Comfort,et al.  A dynamic decision support system based on geographical information and mobile social networks: A model for tsunami risk mitigation in Padang, Indonesia , 2016 .

[12]  Jeffrey Heer,et al.  SpanningAspectRatioBank Easing FunctionS ArrayIn ColorIn Date Interpolator MatrixInterpola NumObjecPointI Rectang ISchedu Parallel Pause Scheduler Sequen Transition Transitioner Transiti Tween Co DelimGraphMLCon IData JSONCon DataField DataSc Dat DataSource Data DataUtil DirtySprite LineS RectSprite , 2011 .

[13]  Huiji Gao,et al.  Harnessing the Crowdsourcing Power of Social Media for Disaster Relief , 2011, IEEE Intelligent Systems.

[14]  Damon P. Coppola.  Introduction to International Disaster Management , 2006 .

[15]  Ayu Purwarianti,et al.  Indonesian social media sentiment analysis with sarcasm detection , 2013, 2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[16]  Mario Antonius Birowo.  The use of community radio in managing natural disaster in Indonesia , 2010 .

[17]  Maulahikmah Galinium,et al.  Automatic mood classification of Indonesian tweets using linguistic approach , 2013, 2013 International Conference on Information Technology and Electrical Engineering (ICITEE).

[18]  Mohammad Ali Abbasi,et al.  TweetTracker: An Analysis Tool for Humanitarian and Disaster Relief , 2011, ICWSM.

[19]  Yutaka Matsuo,et al.  Earthquake shakes Twitter users: real-time event detection by social sensors , 2010, WWW '10.

[20]  Huan Liu,et al.  Is the Sample Good Enough? Comparing Data from Twitter's Streaming API with Twitter's Firehose , 2013, ICWSM.

[21]  Cory L. Armstrong,et al.  Now Tweet This: How News Organizations Use Twitter , 2010 .

[22]  Taieb Znati,et al.  A cost-effective, environmentally-aware undersea infrastructure to enhance community resilience to tsunamis , 2016 .

[23]  P. Earle,et al.  OMG Earthquake! Can Twitter Improve Earthquake Response? , 2009 .

[24]  Kathleen M. Carley,et al.  Crowd sourcing disaster management: The complex nature of Twitter usage in Padang Indonesia , 2016 .

[25]  Philip D. Wasserman,et al.  Neural networks. II. What are they and why is everybody so interested in them now? , 1988, IEEE Expert.

[26]  Chien-leng Hsu,et al.  Sociology of Hyperlink Networks of Web 1.0, Web 2.0, and Twitter: A Case Study of South Korea , 2011 .

[27]  Leysia Palen,et al.  Trial by fire: The deployment of trusted digital volunteers in the 2011 shadow lake fire , 2012, ISCRAM.

[28]  Huan Liu,et al.  The fragility of Twitter social networks against suspended users , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[29]  Akemi Takeoka Chatfield,et al.  Twitter tsunami early warning network : a social network analysis of Twitter information flows , 2012 .

[30]  Sarah Vieweg,et al.  Situational Awareness in Mass Emergency: A Behavioral and Linguistic Analysis of Microblogged Communications , 2012 .