People are using social media to a greater extent, particularly in emergency situations. However, approaches for processing and analyzing the vast quantities of data produced currently lag far behind. In this paper we discuss important steps, and the associated challenges, for processing and analyzing social media in emergencies. In our research project EmerGent, a huge volume of low-quality messages will be continuously gathered from a variety of social media services such as Facebook or Twitter. Our aim is to design a software system that will process and analyze social media data, transforming the high volume of noisy data into a low volume of rich content that is useful to emergency personnel. Therefore, suitable techniques are needed to extract and condense key information from raw social media data, allowing detection of relevant events and generation of alerts pertinent to emergency personnel.

Event recognition systems have high potential to support crisis management and emergency response. For large-scale scenarios, however, the sheer amount of possible audio and video channels requires adequate processing of the material by automatic means. In this article, the authors focus on automatic audio and video event recognition, by means of detecting abnormalities both in train noise as well as surveillance videos, and by conducting automatic speech recognition on fire fighter communication. All components are integrated in an overall intelligent resource management system. The authors elaborate on the challenges expected from real life data and the solutions that the authors applied. The overall system, based on Event-Driven Service-Oriented Architecture, has been implemented and partly integrated into the end users' infrastructures. The system has been continuously running for more than two years, collecting data for research purposes.

No abstract

No abstract