Analyzing Social media in crisis management using expertise feedback modelling

International audienceCurrently social media are largely used in interactions, especially in crisis situations. We note a big volume of interactions around events. Observing these interactions give information even to alert the existence of an incident, event, or to understand the expansion of a problem. Crisis management actors observe social media to be aware about this type of information in order to consider them in their decisions. Specific organizations are founded in order to observe social media interactions and send their analysis to rescue and crisis management actors. In our work, an experience feedback of this type of organizations as VISOV, a crisis social media analysis association, is capitalized. First results show main concepts used in their investigations. These concepts are then used as keywords to explore social media using Text Mining. IMPLIC-R system is developed to link Protégé (Ontologie management system) and R-studio (Text Mining tools) in order to simulate some social media investigations in crisis management. This system will be integrated in CRIMSON, a crisis management support system