What to Expect When the Unexpected Happens

Abstract

The use of social media to communicate timely information during crisis situations has become a common practice in recent years. In particular, the one-to-many nature of Twitter has created an opportunity for stakeholders to disseminate crisis-relevant messages, and to access vast amounts of information they may not otherwise have. Our goal is to understand what affected populations, response agencies and other stakeholders can expect-and not expect-from these data in various types of disaster situations. Anecdotal evidence suggests that different types of crises elicit different reactions from Twitter users, but we have yet to see whether this is in fact the case. In this paper, we investigate several crisesincluding natural hazards and human-induced disasters-in a systematic manner and with a consistent methodology. This leads to insights about the prevalence of different information types and sources across a variety of crisis situations.

The role of unstructured data in real-time disaster-related social media monitoring

“…It is widely used in the study of natural disasters (see: [5], [9]- [11], [13]). Because the basic form of communication on Twitter (the limited length tweet) is essentially a broadcast, the platform is especially suitable for the emergency management use case: relevant keywords and hashtags (characteristic user-generated metadata tags) can be monitored and related content from most users can be extracted and analyzed in near real-time.…”

“…Previous literature provides different types of classifications, in terms of Informativeness and Information Type, that can potentially generalize to multiple events (see [9] A document, related to any hazard, can belong to a single, multiple or none of these classes. Informativeness notion, originally tied to awareness and usefulness during an event (see [9]), had instead to be revised to operate in the more generic context we propose.…”

“…In the work done by Olteanu et al [9], the authors present the result of a manual labeling campaign to describe what to expect from social media data across a variety of emergencies (natural disasters, terrorist attacks, explosions, etc.) in terms of volume, informative level, type and source.…”

“…Starting from previous work, that forms the basis for our research (Olteanu et al [9] in particular), we consider two main categories of information to be extracted and that constitute the key features of the classification model we employ:…”

A Fundamentally Confused Document: Situation Reports and the Work of Producing Humanitarian Information

“…Social media such as Twitter are potentially useful to professional disaster response activity [43], but other forms social media are already influential amongst professional disaster responders. Open Street Map (OSM), annotated by volunteers, is being used by humanitarian workers in the context of relief work [44].…”