Melanie Eckle, Benjamin Herfort, Yingwei Yan, Chiao-Ling Kuo, & Alexander Zipf. (2017). Towards using Volunteered Geographic Information to monitor post-disaster recovery in tourist destinations. In eds Aurélie Montarnal Matthieu Lauras Chihab Hanachi F. B. Tina Comes (Ed.), Proceedings of the 14th International Conference on Information Systems for Crisis Response And Management (pp. 1008–1019). Albi, France: Iscram.
Abstract: The aftereffects of disaster events are significant in tourist destinations where they do not only lead to destruction and casualties, but also long-lasting economic harms. The public perception causes tourists to refrain from visiting these areas and recovery of the tourist industry, a major economic sector, to become challenging. To improve this situation, current information about the tourist and infrastructure recovery is crucial for a “rebranding”- information that is however time and cost-intensive in acquisition using traditional information sources. An alternative data source that has shown great potential for information gathering in other disaster management phases, which was less considered for disaster recovery purposes, is Volunteered Geographic Information (VGI). Therefore, this paper introduces a VGI-based methodology to address this task. Initial analyses conducted with Flickr data indicate a potential of VGI for recovery monitoring, whereas the analysis of OpenStreetMap data shows, that this form of VGI requires further quality assurance.
|
|
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.
Abstract: 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.
|
|
Sophia B. Liu, Leysia Palen, Jeannette N. Sutton, Amanda L. Hughes, & Sara Vieweg. (2008). In search of the bigger picture: The emergent role of on-line photo sharing in times of disaster. In B. V. de W. F. Fiedrich (Ed.), Proceedings of ISCRAM 2008 – 5th International Conference on Information Systems for Crisis Response and Management (pp. 140–149). Washington, DC: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Eyewitness photography is increasingly playing a more significant role in disaster response and recovery efforts. This research elaborates on the ways in which members of the public participate during times of disaster by closely examining the evolving role of a prominent photo-sharing website, Flickr, in events that have occurred since its launch in February 2004. We discuss features of Flickr's emerging evolutionary growth as a community forum for disaster-related grassroots activity based on the findings from our qualitative study of 29 groups across six disasters over Flickr's nearly three-year lifespan. Our findings discuss efforts toward the development of norms that attempt to guide the nature of social practice around photographic content during disaster response and recovery efforts.
|
|
Suradej Intagorn, Anon Plangprasopchok, & Kristina Lerman. (2010). Harvesting geospatial knowledge from social metadata. In C. Zobel B. T. S. French (Ed.), ISCRAM 2010 – 7th International Conference on Information Systems for Crisis Response and Management: Defining Crisis Management 3.0, Proceedings. Seattle, WA: Information Systems for Crisis Response and Management, ISCRAM.
Abstract: Up-to-date geospatial information can help crisis management community to coordinate its response. In addition to data that is created and curated by experts, there is an abundance of user-generated, user-curated data on Social Web sites such as Flickr, Delicious, and Google Earth, that can be used to harvest knowledge to solve real-world problems. User-generated, or social, metadata can be used to learn concepts and relations between them that can improve information discovery, and data integration and management. We describe a method that aggregates social metadata created by thousands of users of the social photo-sharing site Flickr to learn geospatial concepts and relations. Our method leverages geotagged data to represent and reason about places. We evaluate learned geospatial relations by comparing them to a reference ontology provided by GeoNames.org. We show that our approach achieves good performance and also learns useful information that does not appear in the reference ontology.
|
|