In this paper, we propose a semantic approach for monitoring information publishedon social networks about a specific event. In the era of Big Data, when an emergencyoccurs information posted on social networks becomes more and more helpful foremergency operators. As direct witnesses of the situation, people share photos, videosor text messages about events that call their attention. In the emergency operationcenter, these data can be collected and integrated within the management processto improve the overall understanding of the situation and in particular of the citizenreactions. To support the tracking and analyzing of social network activities, there arealready monitoring tools that combine visualization techniques with geographicalmaps. However, tweets are written from the perspective of citizens and the informationthey provide might be inaccurate, irrelevant or false. Our approach tries to dealwith data relevance proposing an innovative ontology-based method for filteringtweets and extracting meaningful topics depending on their semantic content. In thisway data become relevant for the operators to make decisions. Two real cases used totest its applicability showed that different visualization techniques might be neededto support situation awareness. This ontology-based approach can be generalizedfor analyzing the information flow about other domains of application changing theunderlying knowledge base.
Information visualization Information categorization Emergency management Semantic modeling Ontologies