Fatehkia, M., Imran, M., & Weber, I. (2023). Towards Real-time Remote Social Sensing via Targeted Advertising. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 396–406). Omaha, USA: University of Nebraska at Omaha.
Abstract: Social media serves as an important communication channel for people affected by crises, creating a data source for emergency responders wanting to improve situational awareness. In particular, social listening on Twitter has been widely used for real-time analysis of crisis-related messages. This approach, however, is often hindered by the small fraction of (hyper-)localized content and by the inability to explicitly ask affected populations about aspects with the most operational value. Here, we explore a new form of social media data collected through targeted poll ads on Facebook. Using geo-targeted ads during flood events in six countries, we show that it is possible to collect thousands of poll responses within hours of launching the ad campaign, and at a cost of a few (US dollar) cents per response. We believe that this flexible, fast, and affordable data collection can serve as a valuable complement to existing approaches.
|
|
Rob Grace, & Michelle Potts. (2022). Opportunities for Multisensor Integration in Public-Safety Answering Points. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 895–904). Tarbes, France.
Abstract: Public-Safety Answering Points (PSAPs) coordinate emergency response by gathering critical information from 911 callers for dispatch to first responders. However, PSAPs fail to gather this information if 911 callers are unable, unwilling, or unavailable to report key details about an emergency. To address this problem, early-adopter PSAPs employ communication specialists to gather multimedia information from multiple sensing tools, including automated alarms, cameras, government databases, location systems, open-source websites, social media, and alternative communication channels such as text-to-911. Using preliminary usage data from an early- adopter PSAP, this study identifies 11 breakdowns in 911 call taking that create opportunities for multisensor integration. This study then characterizes use cases for multisensor tools based on usage patterns observed across five incident types. These findings highlight multisensor integration as a critical area for crisis informatics research.
|
|
Zainab Akhtar, Ferda Ofli, & Muhammad Imran. (2021). Towards Using Remote Sensing and Social Media Data for Flood Mapping. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 536–551). Blacksburg, VA (USA): Virginia Tech.
Abstract: Ghana's capital, the Greater Accra Metropolitan Area (GAMA) is most vulnerable to flooding due to its high population density. This paper proposes the fusion of satellite imagery, social media, and geospatial data to derive near real-time (NRT) flood maps to understand human activity during a disaster and the extent of infrastructure damage. To that end, the paper presents an automatic thresholding technique for NRT flood mapping using Sentinel-1 images where four different speckle filters are compared using the VV, VH and VV/VH polarization to determine the best polarization(s) for delineating flood extents. The VV and VH bands together on Perona-Malik filtered images achieved the highest accuracy with an F1-score of 81.6%. Moreover, all tweet text and images were found to be located in flooded regions or in very close proximity to a flooded region, thus allowing crisis responders to better understand vulnerable communities and what humanitarian action is required.
|
|
Artur Ricardo Bizon, Luciana P. de Araújo Kohler, Adilson Luiz Nicoletti, Fernanda Dal Bosco, Murilo Schramm da Silva, & Thales Bohn Pessatti. (2020). Integration statistical systems for land cover mapping in Southern Brazil. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 498–505). Blacksburg, VA (USA): Virginia Tech.
Abstract: The remote sensing is a way to optimize the process of land cover classification allowing that this process will be by high definition images of satellite. For the research it was used the Google Earth Engine with JavaScript programming language to classify the images, identifying the areas with forest or reforest. It was identified that classifiers Random Forest and Logistic Regression have a high performance in classify the images. From them it was developed functions to process automatically of new images with purpose of classify them in relation to land cover.
|
|
Flavio Horita, Ricardo Vilela, Renata Martins, Danielle Bressiani, Gilca Palma, & João Porto de Albuquerque. (2018). Determining flooded areas using crowd sensing data and weather radar precipitation: a case study in Brazil. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 1040–1050). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: Crowd sensing data (also known as crowdsourcing) are of great significance to support flood risk management. With the growing volume of available data in the past few years, researchers have used in situ sensor data to filter and prioritize volunteers' information. Nevertheless, stationary, in situ sensors are only capable of monitoring a limited region, and this could hamper proper decision-making. This study investigates the use of weather radar precipitation to support the processing of crowd sensing data with the goal of improving situation awareness in a disaster and early warnings (e.g., floods). Results from a case study carried out in the city of São Paulo, Brazil, demonstrate that weather radar data are able to validate flooded areas identified from clusters of crowd sensing data. In this manner, crowd sensing and weather radar data together can not only help engage citizens, but also generate high-quality data at finer spatial and temporal resolutions to improve the decision-making related to weather-related disaster events.
|
|