Christoph Amelunxen, Marc-André Kaufhold, Annika Schubert, Nicola Rupp, Matthias Habdank, Christian Reuter
Social media data might be of value for emergency services. However, many studies have iden-tified barriers regarding the high amount of data, also called big social data (Olshannikova, Olsson, Huhtamäki, & Kärkkäinen, 2017), emergency services need to deal with before, during and after emergencies. In our project the strategy is to process and analyse social media data streams before, during and after emergencies including the steps of (A) information gathering (incl. data preparation), (B) data enrichment, (C) semantic information modelling with ontolo-gies and information mining, (E) information quality and (F) alert detection (Reuter, Amelunxen, & Moi, 2016). In this deliverable, we present two iterations of evaluation of our concept, which has been implemented as a prototype for emergency services.