1.1
1
xml
info:srw/schema/1/mods-v3.2
Tweedr: Mining twitter to inform disaster response
Zahra Ashktorab
author
Christopher Brown
author
Manojit Nandi
author
Aron Culotta
author
2014
The Pennsylvania State University
University Park, PA
English
In this paper, we introduce Tweedr, a Twitter-mining tool that extracts actionable information for disaster relief workers during natural disasters. The Tweedr pipeline consists of three main parts: classification, clustering and extraction. In the classification phase, we use a variety of classification methods (sLDA, SVM, and logistic regression) to identify tweets reporting damage or casualties. In the clustering phase, we use filters to merge tweets that are similar to one another; and finally, in the extraction phase, we extract tokens and phrases that report specific information about different classes of infrastructure damage, damage types, and casualties. We empirically validate our approach with tweets collected from 12 different crises in the United States since 2006.
Data mining
Disaster prevention
Disasters
Extraction
Filtration
Information systems
Social networking (online)
Classification methods
Disaster response
Extraction phase
Logistic regressions
Natural disasters
Social media
Specific information
Text mining
Emergency services
exported from refbase (http://idl.iscram.org/show.php?record=275), last updated on Tue, 04 Aug 2015 12:23:02 +0200
text
http://idl.iscram.org/files/ashktorab/2014/275_Ashktorab_etal2014.pdf
ZahraAshktorab_etal2014
ISCRAM 2014 Conference Proceedings – 11th International Conference on Information Systems for Crisis Response and Management
ISCRAM 2014
S.R. Hiltz
M
S
Pfaff
editor
11th International ISCRAM Conference on Information Systems for Crisis Response and Management
2014
The Pennsylvania State University
University Park, PA
conference publication
354
358
9780692211946
2411-3387
1