Improving Situational Awareness in Emergencies through Crowd Supported Analysis of Social Media

Abstract

In this ongoing research project, we develop an information system that aims to improve situational awareness and shorten response times in emergency response situations. Through a combination of algorithmic and crowdsourcing techniques, the proposed system gathers, analyzes, organizes and then visualizes social media activity around an event in real-time and turns overwhelming streams of status updates into actionable pieces of information. This document is an extended abstract to the poster with the same name. Social media in emergency response Successful emergency response relies heavily on situational awareness, created from access to timely, accurate and relevant information about complex ongoing events. As a complement to traditional sources, researchers (Vieweg et al. 2010) and emergency response professionals (van der Vlugt and Hornery 2009) are now identifying social media as an emerging source of early breaking news, image and video footage, and an indicator of where to direct resources. However, existing information systems either fail to incorporate social media as a source, or do not meet the requirements imposed by use in crisis situations. Algorithms vs. crowdsourcing There are currently two main approaches for building real-time information systems. Purely automated news aggregators, such as EMM NewsBrief (Piskorki et al. 2008), already perform quite well at the task of gathering and clustering articles related to an event, including extracting metadata such as locations, people and quotes from the clusters. However, these systems offer generic approaches that are unable to gather and present knowledge in a manner tailored to the characteristics, needs and priorities of a specific event or disaster. Although social media aggregators exist, we are unaware of any that offer functionality and performance on a level similar to those for news. Other systems more specialized for emergency use, such as Ushahidi (www.ushahidi.com), adopt an almost purely crowdsourced approach by relying on individuals to submit reports containing all necessary metadata; data which is then presented using default or in some cases event-adapted interfaces. While these systems are designed to be much more adaptive than the news aggregators, they are instead unable to integrate the vast but largely unstructured knowledge base related to a particular disaster that is social and traditional media.