Evolution of communities on Twitter and the role of their leaders during emergencies

Twitter is presently utilized as a channel of communication and information dissemination. At present, government and non-government emergency management organizations utilize Twitter to disseminate emergency relevant information. However, these organizations have limited ability to evaluate the Twitter communication in order to discover communication patterns, key players, and messages that are being propagated through Twitter regarding the event. More importantly there is a general lack of knowledge of who are the individuals or organizations that disseminate warning information, provide confirmations of an event and associated actions, and urge others to take action. This paper presents a methodology that shows how Natural Language Processing (NLP) and Social Network Analysis (SNA) can aid in addressing these issues. The methodology, in addition to qualitative data collected during on-site interviews and publicly available information, was successfully applied to a Twitter data set collected during 2011 Japan tsunami. NLP techniques were applied to extract actionable messages. Based on the messages extracted by NLP, SNA was used to construct a network of actionable messages. While SNA discovered communities and extracted the community leaders, NLP was used to determine the behavior of the community members and the role of the community leaders. Therefore, the proposed methodology automatically finds communities, evaluates its members' behaviors, and authenticates cohesive behaviors of the community members during emergencies. Moreover, the methodology efficiently finds the leaders of the communities, while also identifying their role in communities.

[1]  Heng Ji,et al.  Joint Event Extraction via Structured Prediction with Global Features , 2013, ACL.

[2]  James Allan,et al.  Detections , Bounds , and Timelines : UMass and TDT-3 , 2000 .

[3]  Leysia Palen,et al.  "Beacons of hope" in decentralized coordination: learning from on-the-ground medical twitterers during the 2010 Haiti earthquake , 2012, CSCW.

[4]  Dennis S. Mileti,et al.  Communication of Emergency Public Warnings: A Social Science Perspective and State-of-the-Art Assessment , 1990 .

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

[6]  P. Bonacich.  Power and Centrality: A Family of Measures , 1987, American Journal of Sociology.

[7]  Heng Ji,et al.  Refining Event Extraction through Cross-Document Inference , 2008, ACL.

[8]  Oren Etzioni,et al.  Open domain event extraction from twitter , 2012, KDD.

[9]  Jon M. Kleinberg,et al.  The Directed Closure Process in Hybrid Social-Information Networks, with an Analysis of Link Formation on Twitter , 2010, ICWSM.

[10]  Fang Wu,et al.  Social Networks that Matter: Twitter Under the Microscope , 2008, First Monday.

[11]  Heng Ji,et al.  Exploiting Background Information Networks to Enhance Bilingual Event Extraction Through Topic Modeling , 2011 .

[12]  Dave Yates,et al.  Emergency knowledge management and social media technologies: A case study of the 2010 Haitian earthquake , 2011, Int. J. Inf. Manag..

[13]  Santo Fortunato,et al.  Community detection in graphs , 2009, ArXiv.

[14]  Xiang Li,et al.  Domain-Independent Novel Event Discovery and Semi-Automatic Event Annotation , 2010, PACLIC.

[15]  Leysia Palen,et al.  "Voluntweeters": self-organizing by digital volunteers in times of crisis , 2011, CHI.

[16]  Miles Osborne,et al.  Streaming First Story Detection with application to Twitter , 2010, NAACL.

[17]  Jon Kleinberg,et al.  Differences in the mechanics of information diffusion across topics: idioms, political hashtags, and complex contagion on twitter , 2011, WWW.

[18]  Linton C. Freeman,et al.  The gatekeeper, pair-dependency and structural centrality , 1980 .

[19]  Ee-Peng Lim,et al.  Analyzing feature trajectories for event detection , 2007, SIGIR.

[20]  Santo Fortunato,et al.  Finding Statistically Significant Communities in Networks , 2010, PloS one.

[21]  William A. Wallace,et al.  Actionable Information during Extreme Events -- Case Study: Warnings and 2011 Tohoku Earthquake , 2012, 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing.

[22]  Ray Reagans,et al.  Network Structure and Knowledge Transfer: The Effects of Cohesion and Range , 2003 .

[23]  John Scott.  What is social network analysis , 2010 .

[24]  Yiming Yang,et al.  A study of retrospective and on-line event detection , 1998, SIGIR '98.

[25]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[26]  R. Burt.  Structural Holes versus Network Closure as Social Capital , 2001 .

[27]  Regina Barzilay,et al.  Event Discovery in Social Media Feeds , 2011, ACL.

[28]  Stanley Wasserman,et al.  Social Network Analysis: Methods and Applications , 1994, Structural analysis in the social sciences.

[29]  Piotr Indyk,et al.  Approximate nearest neighbors: towards removing the curse of dimensionality , 1998, STOC '98.

[30]  James Allan,et al.  First story detection in TDT is hard , 2000, CIKM '00.

[31]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[32]  L. Freeman.  Centrality in social networks conceptual clarification , 1978 .

[33]  Marion Verweij.  Beacons of Hope , 2002 .

[34]  Michael K Lindell,et al.  The Protective Action Decision Model: Theoretical Modifications and Additional Evidence , 2012, Risk analysis : an official publication of the Society for Risk Analysis.

[35]  Matthieu Latapy,et al.  Computing Communities in Large Networks Using Random Walks , 2004, J. Graph Algorithms Appl..

[36]  Bu-Sung Lee,et al.  Event Detection in Twitter , 2011, ICWSM.