|
Samuel Lee Toepke. (2018). Leveraging Elasticsearch and Botometer to Explore Volunteered Geographic Information. In Kees Boersma, & Brian Tomaszeski (Eds.), ISCRAM 2018 Conference Proceedings – 15th International Conference on Information Systems for Crisis Response and Management (pp. 663–676). Rochester, NY (USA): Rochester Institute of Technology.
Abstract: In the past year, numerous weather-related disasters have continued to display the critical importance of crisis management and response. Volunteered geographic information (VGI) has been previously shown to provide illumination during all parts of the disaster timeline. Alas, for a geospatial area, the amount of data provided can cause information overload, and be difficult to process/visualize. This work presents a set of open-source tools that can be easily configured, deployed and maintained, to leverage data from Twitter's streaming service. The user interface presents data in near real-time, and allows for dynamic queries, visualizations, maps and dashboards. Another VGI challenge is quantifying trustworthiness of the data. The presented work shows integration of a Twitter-bot assessment service, which uses several heuristics to determine the bot-ness of a Twitter account. Architecture is described, Twitter data from a major metropolitan area is explored using the tools, and conclusions/follow-on work are discussed.
|
|
|
Samuel Lee Toepke. (2017). Temporal Sampling Implications for Crowd Sourced Population Estimations from Social Media. 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. 564–571). Albi, France: Iscram.
Abstract: Understanding the movements of a population throughout the 24-hour day is critical when directing disaster response in an urban area. An emergency situation can develop rapidly, and understanding the expected locations of groups of people is required for the success of first responders. Recent advances in modern consumer technologies have facilitated the generation, sharing and mining of an extensive amount of volunteered geographic information. Users leverage inexpensive smart devices, pervasive Internet connections and social media services to provide data about geospatial locations. Using an enterprise system, it is possible to aggregate this freely available, geospatially enabled data and create a population estimation with high spatiotemporal resolution, via a heat map. This investigation explores the effects of different temporal sampling periods when creating such estimations. Time periods are selected, estimations are generated for several large urban areas in the western United States, and comparisons of the results are shown/discussed.
|
|
|
Samuel Lee Toepke, & R. Scott Starsman. (2015). Population Distribution Estimation of an Urban Area Using Crowd Sourced Data for Disaster Response. In L. Palen, M. Buscher, T. Comes, & A. Hughes (Eds.), ISCRAM 2015 Conference Proceedings ? 12th International Conference on Information Systems for Crisis Response and Management. Kristiansand, Norway: University of Agder (UiA).
Abstract: In the event of a disaster, high resolution knowledge of expected population distribution is a boon to the situational awareness of disaster managers and first responders. Knowing the expected locations of large throngs of people can greatly affect distribution of aid and response infrastructure. Effective dissemination of this information can be realized by using a myriad of readily available technologies.
With the modern proliferation of smart phones, pervasive Internet and freely available social media applications, population distribution can be estimated from the constant aggregation of crowd sourced data. Twitter and Instagram both publish geolocated data, which is then processed by a cloud-based, enterprise application to generate heat maps. The heat maps are then shown in a real-time geographic information system that is visible to any mobile device with a web browser.
|
|