NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED549430
Record Type: Non-Journal
Publication Date: 2012
Pages: 300
Abstractor: As Provided
Reference Count: N/A
ISBN: 978-1-2673-3596-8
ISSN: N/A
Situational Awareness in Mass Emergency: A Behavioral and Linguistic Analysis of Microblogged Communications
Vieweg, Sarah Elizabeth
ProQuest LLC, Ph.D. Dissertation, University of Colorado at Boulder
In times of mass emergency, users of Twitter (a popular microblogging service) often communicate information about the event, some of which contributes to situational awareness. Situational awareness refers to a state of understanding the "big picture" in time- and safety-critical situations. The more situational awareness people have, the better equipped they are to make informed decisions. Given that hundreds of millions of Twitter communications (known as "tweets") are sent every day and emergency events regularly occur, automated methods are needed to identify those tweets that contain actionable, tactical information. The purpose of this dissertation is to explore how Twitter is used in mass emergencies, and to inform mechanisms for automatically identifying information that contributes to situational awareness. This dissertation provides a three-part analysis of Twitter communications from four different mass emergency situations. I first perform discourse analysis on tweet content to uncover and explain the information Twitter users communicate during mass emergencies. This analysis serves as the basis for a qualitative coding scheme of specific information types that lead to situational awareness. Second, using this coding scheme, tweets from each of the four emergency events are coded by multiple annotators and inter-annotator agreement rates are calculated. The results of this process provide an overview of the information Twitter users contribute in these emergency situations. My final analysis identifies linguistic characteristics of those tweets that convey situational awareness information and serves as a foundation for natural language processing classifiers that can be trained to identify such tweets. In sum, this dissertation contributes (1) an analysis of tweet content that is relevant to situational awareness, (2) an overview of the information Twitter users communicate that contributes to situational awareness, and (3) a computational linguistic resource for the development of natural language processing tools that automatically extract tweets containing information relevant to situational awareness. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]
ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Publication Type: Dissertations/Theses - Doctoral Dissertations
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A