1.1
1
xml
info:srw/schema/1/dc-v1.1
Mining and Classifying Image Posts on Social Media to Analyse Fires
Shannon Daly
James A. Thom
A. Tapia
P. Antunes
V.A. Bañuls
K. Moore
J. Porto
We propose a methodology to study the occurrence of fires through image posts on Flickr; crowd-sourcing information from a noisy social media dataset can estimate the presence of fires. We collect several years worth of photos and associated metadata using fire-related search terms. We use an image classification model to detect geotagged photos that are further analysed to determine if a fire event did occur at a particular time and place. Furthermore, a case study investigates image features and spatio-temporal elements in the metadata, as well as location information contained in camera EXIF data.
urn:ISBN:978-84-608-7984-9
openurl:?ctx_ver=Z39.88-2004&rfr_id=info%3Asid%2Fidl.iscram.org%2F&genre=proceeding&title=Mining%20and%20Classifying%20Image%20Posts%20on%20Social%20Media%20to%20Analyse%20Fires&stitle=ISCRAM%202016&issn=2411-3388&isbn=978-84-608-7984-9&date=2016&aulast=Shannon%20Daly&au=James%20A.%20Thom&pub=Federal%20University%20of%20Rio%20de%20Janeiro&place=Rio%20de%20Janeiro%2C%20Brasil&sid=refbase%3AISCRAM
url:http://idl.iscram.org/show.php?record=1395
citekey:ShannonDaly+JamesA.Thom2016
citation:Shannon Daly, & James A. Thom. (2016). Mining and Classifying Image Posts on Social Media to Analyse Fires. In A. Tapia, P. Antunes, V.A. Bañuls, K. Moore, & J. Porto (Eds.), ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management. Rio de Janeiro, Brasil: Federal University of Rio de Janeiro.
2016
ConferencePaper
text
Flickr
Image Analytics
Geotags
Geocoding
file:http://idl.iscram.org/files/shannondaly/2016/1395_ShannonDaly2016.pdf
Federal University of Rio de Janeiro
English
2411-3388
ISCRAM 2016 Conference Proceedings ? 13th International Conference on Information Systems for Crisis Response and Management
2016
1