Assessing relevance of tweets for risk communication
Abstract
Although Twitter is used for emergency management activities, the relevance of tweets during a hazard event is still open to debate. Here in this study, six different computational (i.e. Natural Language Processing) and spatiotemporal analytical approaches were implemented to assess the relevance of risk information extracted from tweets obtained during the 2013 Colorado flood event. Primarily, tweets containing information about the flooding events and its impacts were analysed. Examination of the relationships between tweet volume and its content with precipitation amount, damage extent, and official reports revealed that relevant tweets provided information about the event and its impacts rather than any other risk information that public expects to receive via alert messages. However, only 14% of the geo-tagged tweets and only 0.06% of the total fire hose tweets were found to be relevant to the event. By providing insight into the quality of social media data and its usefulness to emergency management activities, this study contributes to the literature on quality of big data. Future research in this area would focus on assessing the reliability of relevant tweets for disaster related situational awareness.
- Authors:
-
- Dalhousie Univ., Halifax, NS (Canada). Resilience Research Centre
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Urban Dynamics Inst., Computational Sciences and Engineering Division
- Univ. of Southern Mississippi, Hattiesburg, MS (United States). School of Computing
- Univ. of Southern Mississippi, Hattiesburg, MS (United States). Dept. of Geography and Geology
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE; National Science Foundation (NSF); US Department of Homeland Security (DHS)
- OSTI Identifier:
- 1471917
- Grant/Contract Number:
- AC05-00OR22725; CMMI-1335187; HSHQDC-12-C-00057
- Resource Type:
- Accepted Manuscript
- Journal Name:
- International Journal of Digital Earth
- Additional Journal Information:
- Journal Volume: 12; Journal Issue: 7; Journal ID: ISSN 1753-8947
- Publisher:
- Taylor & Francis
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Content relevance; Twitter; spatiotemporal data mining; emergency management; risk communication
Citation Formats
Liu, Xiaohui, Kar, Bandana, Zhang, Chaoyang, and Cochran, David M. Assessing relevance of tweets for risk communication. United States: N. p., 2018.
Web. doi:10.1080/17538947.2018.1480670.
Liu, Xiaohui, Kar, Bandana, Zhang, Chaoyang, & Cochran, David M. Assessing relevance of tweets for risk communication. United States. https://doi.org/10.1080/17538947.2018.1480670
Liu, Xiaohui, Kar, Bandana, Zhang, Chaoyang, and Cochran, David M. Fri .
"Assessing relevance of tweets for risk communication". United States. https://doi.org/10.1080/17538947.2018.1480670. https://www.osti.gov/servlets/purl/1471917.
@article{osti_1471917,
title = {Assessing relevance of tweets for risk communication},
author = {Liu, Xiaohui and Kar, Bandana and Zhang, Chaoyang and Cochran, David M.},
abstractNote = {Although Twitter is used for emergency management activities, the relevance of tweets during a hazard event is still open to debate. Here in this study, six different computational (i.e. Natural Language Processing) and spatiotemporal analytical approaches were implemented to assess the relevance of risk information extracted from tweets obtained during the 2013 Colorado flood event. Primarily, tweets containing information about the flooding events and its impacts were analysed. Examination of the relationships between tweet volume and its content with precipitation amount, damage extent, and official reports revealed that relevant tweets provided information about the event and its impacts rather than any other risk information that public expects to receive via alert messages. However, only 14% of the geo-tagged tweets and only 0.06% of the total fire hose tweets were found to be relevant to the event. By providing insight into the quality of social media data and its usefulness to emergency management activities, this study contributes to the literature on quality of big data. Future research in this area would focus on assessing the reliability of relevant tweets for disaster related situational awareness.},
doi = {10.1080/17538947.2018.1480670},
journal = {International Journal of Digital Earth},
number = 7,
volume = 12,
place = {United States},
year = {Fri Jun 01 00:00:00 EDT 2018},
month = {Fri Jun 01 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Beyond Accuracy: What Data Quality Means to Data Consumers
journal, March 1996
- Wang, Richard Y.; Strong, Diane M.
- Journal of Management Information Systems, Vol. 12, Issue 4
The Elephant in the JIC: The Fundamental Flaw of Emergency Public Information within the NIMS Framework
journal, January 2010
- Crowe, Adam
- Journal of Homeland Security and Emergency Management, Vol. 7, Issue 1
Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition
conference, October 2012
- Chae, Junghoon; Thom, Dennis; Bosch, Harald
- 2012 IEEE Conference on Visual Analytics Science and Technology (VAST)
Using crowdsourcing for TREC relevance assessment
journal, November 2012
- Alonso, Omar; Mizzaro, Stefano
- Information Processing & Management, Vol. 48, Issue 6
Context relevance assessment and exploitation in mobile recommender systems
journal, June 2011
- Baltrunas, Linas; Ludwig, Bernd; Peer, Stefan
- Personal and Ubiquitous Computing, Vol. 16, Issue 5
Identifying and Mapping Community Vulnerability
journal, March 1999
- Morrow, Betty Hearn
- Disasters, Vol. 23, Issue 1
The Challenges of Data Quality and Data Quality Assessment in the Big Data Era
journal, May 2015
- Cai, Li; Zhu, Yangyong
- Data Science Journal, Vol. 14, Issue 0
Using control data to determine the reliability of volunteered geographic information about land cover
journal, August 2013
- Comber, Alexis; See, Linda; Fritz, Steffen
- International Journal of Applied Earth Observation and Geoinformation, Vol. 23
Does compassion go viral? Social media, caring, and the Fort McMurray wildfire
journal, February 2018
- Boulianne, Shelley; Minaker, Joanne; Haney, Timothy J.
- Information, Communication & Society, Vol. 21, Issue 5
The Fukushima Nuclear Crisis Reemphasizes the Need for Improved Risk Communication and Better Use of Social Media
journal, January 2012
- Ng, Kwan-Hoong; Lean, Mei-Li
- Health Physics, Vol. 103, Issue 3
Weight of Evidence: a framework for the appraisal of the quality and relevance of evidence
journal, May 2007
- Gough, David
- Research Papers in Education, Vol. 22, Issue 2
Social Science Research Needs for the Hurricane Forecast and Warning System
journal, August 2007
- Gladwin, Hugh; Lazo, Jeffrey K.; Morrow, Betty Hearn
- Natural Hazards Review, Vol. 8, Issue 3
Discovery of unusual regional social activities using geo-tagged microblogs
journal, March 2011
- Lee, Ryong; Wakamiya, Shoko; Sumiya, Kazutoshi
- World Wide Web, Vol. 14, Issue 4
Towards an integrated crowdsourcing definition
journal, February 2012
- Estellés-Arolas, Enrique; González-Ladrón-de-Guevara, Fernando
- Journal of Information Science, Vol. 38, Issue 2
Online public communications by police & fire services during the 2012 Hurricane Sandy
conference, January 2014
- Hughes, Amanda L.; St. Denis, Lise A. A.; Palen, Leysia
- Proceedings of the 32nd annual ACM conference on Human factors in computing systems - CHI '14
Emergency knowledge management and social media technologies: A case study of the 2010 Haitian earthquake
journal, February 2011
- Yates, Dave; Paquette, Scott
- International Journal of Information Management, Vol. 31, Issue 1
Social media and disasters: a functional framework for social media use in disaster planning, response, and research
journal, September 2014
- Houston, J. Brian; Hawthorne, Joshua; Perreault, Mildred F.
- Disasters, Vol. 39, Issue 1
Rapid assessment of disaster damage using social media activity
journal, March 2016
- Kryvasheyeu, Yury; Chen, Haohui; Obradovich, Nick
- Science Advances, Vol. 2, Issue 3
Communicating on Twitter during a disaster: An analysis of tweets during Typhoon Haiyan in the Philippines
journal, September 2015
- Takahashi, Bruno; Tandoc, Edson C.; Carmichael, Christine
- Computers in Human Behavior, Vol. 50
Assuring the quality of volunteered geographic information
journal, May 2012
- Goodchild, Michael F.; Li, Linna
- Spatial Statistics, Vol. 1
Risk Communication: An Emerging Area of Health Communication Research
journal, January 1992
- Covello, Vincent T.
- Annals of the International Communication Association, Vol. 15, Issue 1
Obtaining High-Quality Relevance Judgments Using Crowdsourcing
journal, September 2012
- Vuurens, Jeroen B. P.; de Vries, Arjen P.
- IEEE Internet Computing, Vol. 16, Issue 5
The Evolving Role of the Public Information Officer: An Examination of Social Media in Emergency Management
journal, January 2012
- Hughes, Amanda L.; Palen, Leysia
- Journal of Homeland Security and Emergency Management, Vol. 9, Issue 1
From Frequency to Meaning: Vector Space Models of Semantics
journal, January 2010
- Turney, P. D.; Pantel, P.
- Journal of Artificial Intelligence Research, Vol. 37
Quantifying the Digital Traces of Hurricane Sandy on Flickr
journal, November 2013
- Preis, Tobias; Moat, Helen Susannah; Bishop, Steven R.
- Scientific Reports, Vol. 3, Issue 1
Emergency knowledge management and social media technologies: A case study of the 2010 Haitian earthquake: Emergency Knowledge Management and Social Media Technologies: A Case Study of the 2010 Haitian Earthquake
journal, November 2010
- Yates, Dave; Paquette, Scott
- Proceedings of the American Society for Information Science and Technology, Vol. 47, Issue 1
Social Science Research Needs for the Hurricane Forecast and Warning System
journal, January 2009
- Gladwin, Hugh; Lazo, Jeffrey K.; Morrow, Betty Hearn
- Bulletin of the American Meteorological Society, Vol. 90, Issue 1
Works referencing / citing this record:
Social and geographical disparities in Twitter use during Hurricane Harvey
journal, December 2018
- Zou, Lei; Lam, Nina S. N.; Shams, Shayan
- International Journal of Digital Earth, Vol. 12, Issue 11