{"title":"Getting User-Generated Content Structured: Overcoming Information Overload in Emergency Management","authors":"Axel Schulz, J. Ortmann, F. Probst","doi":"10.1109/GHTC.2012.31","DOIUrl":null,"url":null,"abstract":"The amount of real-time user-generated content about disasters and large scale incidents has increased drastically. However, this valuable information source is hardly used by relief organizations for improving emergency response. Currently, relief organizations have little support in filtering and aggregating the overwhelming flood of information. We provide a solution for structuring and merging user-generated content in disaster management, which allows identifying individual incidents in an incoming stream of incident reports. Reports on the same incident are merged using rules that exploit the spatial, temporal and thematic information that is provided in the report. This results in a condensed and easy to consume description of the incident. The thematic aspect is formalized via vocabularies and influences the spatial and temporal extension of the incident representation in our system. The solution is implemented as a client server application, with a mobile application for sending incident reports and a client application to process and store incidents.","PeriodicalId":265555,"journal":{"name":"2012 IEEE Global Humanitarian Technology Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE Global Humanitarian Technology Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GHTC.2012.31","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12
Abstract
The amount of real-time user-generated content about disasters and large scale incidents has increased drastically. However, this valuable information source is hardly used by relief organizations for improving emergency response. Currently, relief organizations have little support in filtering and aggregating the overwhelming flood of information. We provide a solution for structuring and merging user-generated content in disaster management, which allows identifying individual incidents in an incoming stream of incident reports. Reports on the same incident are merged using rules that exploit the spatial, temporal and thematic information that is provided in the report. This results in a condensed and easy to consume description of the incident. The thematic aspect is formalized via vocabularies and influences the spatial and temporal extension of the incident representation in our system. The solution is implemented as a client server application, with a mobile application for sending incident reports and a client application to process and store incidents.