Uncovering sentiment and retweet patterns of disaster-related tweets from a spatiotemporal perspective - A case study of Hurricane Harvey

Abstract Social media has been widely used for emergency communication both in disaster-affected areas and unaffected areas. Comparing emotional reaction and information propagation between on-site users and off-site users from a spatiotemporal perspective can help better comprehend collective human behavior during natural disasters. In this study, we investigate sentiment and retweet patterns of disaster-affected areas and disaster-unaffected areas at different stages of Hurricane Harvey. The results show that off-site tweets were more negative than on-site tweets, especially during the disaster. As for retweet patterns, indifferent-neutral and positive tweets spread broader than mixed-neutral and negative tweets. However, negative tweets spread faster than positive tweets, which reveals that social media users were more sensitive to negative information in disaster situations. With the development of the disaster, social media users were more sensitive to on-site positive messages than off-site negative posts. This data-driven study reveals the significant effect of sentiment expression on the publication and re-distribution of disaster-related messages. It generates implications for emergency communication and disaster management.

[1]  Johnny C. L. Chan,et al.  Global Warming and Western North Pacific Typhoon Activity from an Observational Perspective , 2004 .

[2]  Qunying Huang,et al.  Understanding social media data for disaster management , 2015, Natural Hazards.

[3]  Mihye Seo,et al.  Amplifying Panic and Facilitating Prevention: Multifaceted Effects of Traditional and Social Media Use During the 2015 MERS Crisis in South Korea , 2019, Journalism & Mass Communication Quarterly.

[4]  Daniel P. Aldrich,et al.  Fixing Recovery: Social Capital in Post-Crisis Resilience , 2010 .

[5]  Qunying Huang,et al.  Geographic Situational Awareness: Mining Tweets for Disaster Preparedness, Emergency Response, Impact, and Recovery , 2015, ISPRS Int. J. Geo Inf..

[6]  S. Tagliacozzo.  Government Agency Communication during Postdisaster Reconstruction: Insights from the Christchurch Earthquakes Recovery , 2018 .

[7]  Panos Panagiotopoulos,et al.  Beyond positive or negative: Qualitative sentiment analysis of social media reactions to unexpected stressful events , 2016, Comput. Hum. Behav..

[8]  De Groeve Tom,et al.  Citizens as Sensors for Natural Hazards: A VGI integration Workflow , 2010 .

[9]  Marina Kogan,et al.  Think Local, Retweet Global: Retweeting by the Geographically-Vulnerable during Hurricane Sandy , 2015, CSCW.

[10]  Cornelia Caragea,et al.  Retweetability Analysis and Prediction during Hurricane Sandy , 2016, ISCRAM.

[11]  Hila Becker,et al.  Hip and trendy: Characterizing emerging trends on Twitter , 2011, J. Assoc. Inf. Sci. Technol..

[12]  Leysia Palen,et al.  Supporting disaster reconnaissance with social media data: A design-oriented case study of the 2013 Colorado floods , 2014, ISCRAM.

[13]  Michael J. Paul,et al.  Carmen: A Twitter Geolocation System with Applications to Public Health , 2013 .

[14]  Donald Matheson,et al.  Communication in a Post-Disaster Community: The Struggle to Access Social Capital , 2016 .

[15]  PalenLeysia,et al.  Crisis in a Networked World , 2009 .

[16]  Huan Liu,et al.  A behavior analytics approach to identifying tweets from crisis regions , 2014, HT.

[17]  Shaowen Wang,et al.  Mapping the global Twitter heartbeat: The geography of Twitter , 2013, First Monday.

[18]  J. Fowler,et al.  Rapid assessment of disaster damage using social media activity , 2016, Science Advances.

[19]  Taekyung Kim,et al.  Observation on copying and pasting behavior during the Tohoku earthquake: Retweet pattern changes , 2014, Int. J. Inf. Manag..

[20]  Meerloo Ja.  The biology of laughter. , 1966 .

[21]  Anthony Stefanidis,et al.  Linking cyber and physical spaces through community detection and clustering in social media feeds , 2015, Comput. Environ. Urban Syst..

[22]  Ghazaleh Beigi,et al.  An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief , 2016, Sentiment Analysis and Ontology Engineering.

[23]  Guosong Shao,et al.  Research on Chinese social media users' communication behaviors during public emergency events , 2017, Telematics Informatics.

[24]  ZhangQingpeng,et al.  Characterizing information propagation patterns in emergencies , 2018 .

[25]  Kim Witte,et al.  Fear appeals and persuasion: A review and update of the Extended Parallel Process Model. , 2011 .

[26]  Douglas Yeung,et al.  Building Community Resilience to Disasters: A Way Forward to Enhance National Health Security. , 2011, Rand health quarterly.

[27]  Andrew B. Whinston,et al.  Content Sharing in a Social Broadcasting Environment: Evidence from Twitter , 2014, MIS Q..

[28]  A. Culotta,et al.  A Demographic Analysis of Online Sentiment during Hurricane Irene , 2012 .

[29]  M. Turner,et al.  Motivating Emergency Preparedness Behaviors: The Differential Effects of Guilt Appeals and Actually Anticipating Guilty Feelings , 2012 .

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

[31]  Masahiko Fujii,et al.  A spatiotemporal approach for determining disaster-risk potential based on damage consequences of multiple hazard events , 2014 .

[32]  K. Vohs,et al.  Case Western Reserve University , 1990 .

[33]  S. Sitharama Iyengar,et al.  Data-Driven Techniques in Disaster Information Management , 2017, ACM Comput. Surv..

[34]  Timothy Baldwin,et al.  Text-Based Twitter User Geolocation Prediction , 2014, J. Artif. Intell. Res..

[35]  Pascal Van Hentenryck,et al.  Performance of Social Network Sensors during Hurricane Sandy , 2014, PloS one.

[36]  Ortwin Renn,et al.  The Risk Perception Paradox—Implications for Governance and Communication of Natural Hazards , 2013, Risk analysis : an official publication of the Society for Risk Analysis.

[37]  Claude H. Miller,et al.  Vested Interest, Disaster Preparedness, and Strategic Campaign Message Design , 2015, Health communication.

[38]  Vidhyacharan Bhaskar,et al.  Big data analytics for disaster response and recovery through sentiment analysis , 2018, Int. J. Inf. Manag..

[39]  Tomer Simon,et al.  Socializing in emergencies - A review of the use of social media in emergency situations , 2015, Int. J. Inf. Manag..

[40]  Jun Tian,et al.  Characterizing information propagation patterns in emergencies: A case study with Yiliang Earthquake , 2018, Int. J. Inf. Manag..

[41]  Satoshi Kurihara,et al.  Regional analysis of user interactions on social media in times of disaster , 2013, WWW '13 Companion.

[42]  Cornelia Caragea,et al.  Mapping moods: Geo-mapped sentiment analysis during hurricane sandy , 2014, ISCRAM.

[43]  Stefan Stieglitz,et al.  Emotions and Information Diffusion in Social Media—Sentiment of Microblogs and Sharing Behavior , 2013, J. Manag. Inf. Syst..

[44]  Yusheng Ji,et al.  Intelligent Disaster Response via Social Media Analysis A Survey , 2017, SKDD.

[45]  Gennady L. Andrienko,et al.  Tracing the German centennial flood in the stream of tweets: first lessons learned , 2013, GEOCROWD '13.

[46]  Leysia Palen,et al.  Microblogging during two natural hazards events: what twitter may contribute to situational awareness , 2010, CHI.

[47]  Cornelia Caragea,et al.  Sentiment analysis during Hurricane Sandy in emergency response , 2017 .

[48]  Qunying Huang,et al.  From where do tweets originate?: a GIS approach for user location inference , 2014, LBSN '14.

[49]  Anupam Joshi,et al.  Faking Sandy: characterizing and identifying fake images on Twitter during Hurricane Sandy , 2013, WWW.

[50]  Nastaran Pourebrahim,et al.  Understanding communication dynamics on Twitter during natural disasters: A case study of Hurricane Sandy , 2019, International Journal of Disaster Risk Reduction.

[51]  Vincent A. Knight,et al.  Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack , 2014, Social Network Analysis and Mining.

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

[53]  Xinyue Ye,et al.  Social media analytics for natural disaster management , 2018, Int. J. Geogr. Inf. Sci..

[54]  Serkan Ayvaz,et al.  Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis , 2018, Telematics Informatics.

[55]  Amanda Lee Hughes,et al.  Crisis in a Networked World , 2009 .

[56]  S. Cox,et al.  Citizen-based sensing of crisis events: sensor web enablement for volunteered geographic information , 2013 .

[57]  Julie Barnett,et al.  The social amplification of risk and the hazard sequence: the October 1995 oral contraceptive pill scare , 2003 .

[58]  Eric Fang,et al.  Is Neutral Really Neutral? The Effects of Neutral User-Generated Content on Product Sales , 2014 .

[59]  J. Lerner,et al.  Fear, anger, and risk. , 2001, Journal of personality and social psychology.

[60]  Jintae Lee,et al.  Content features of tweets for effective communication during disasters: A media synchronicity theory perspective , 2019, Int. J. Inf. Manag..

[61]  Michelle R. Guy,et al.  Twitter earthquake detection: earthquake monitoring in a social world , 2012 .

[62]  Kripabandhu Ghosh,et al.  Utilizing microblogs for assisting post-disaster relief operations via matching resource needs and availabilities , 2019, Inf. Process. Manag..

[63]  Petra Saskia Bayerl,et al.  Social media and the police: tweeting practices of british police forces during the August 2011 riots , 2013, CHI.

[64]  Jeannie A. Stamberger,et al.  Crowd sentiment detection during disasters and crises , 2012, ISCRAM.

[65]  Paul M. Torrens,et al.  Uncovering Social Media Reaction Pattern to Protest Events: A Spatiotemporal Dynamics Perspective of Ferguson Unrest , 2015, SocInfo.

[66]  Mike Thelwall,et al.  Sentiment strength detection for the social web , 2012, J. Assoc. Inf. Sci. Technol..

[67]  Lei Zou,et al.  Mining Twitter Data for Improved Understanding of Disaster Resilience , 2018 .

[68]  Andrea Marchetti,et al.  A framework for detecting unfolding emergencies using humans as sensors , 2016, SpringerPlus.

[69]  Cheryl Regehr,et al.  Whatever Gets You Through Today: An Examination of Cynical Humor Among Emergency Service Professionals , 2010 .

[70]  Edward B. Royzman,et al.  Negativity Bias, Negativity Dominance, and Contagion , 2001 .

[71]  Sarah Vieweg,et al.  Processing Social Media Messages in Mass Emergency , 2014, ACM Comput. Surv..

[72]  Hideaki Takeda,et al.  Factors Affecting Retweetability: An Event-Centric Analysis on Twitter , 2014, ICIS.