An Ontology-Based Approach to Social Media Mining for Crisis Management

We describe an existing multilingual information extraction system that automatically detects event information on disasters, conflicts and health threats in near-real time from a continuous flow of on-line news articles. We illustrate a number of strategies for customizing the system to process social media texts such as Twitter messages, which are currently seen as a crucial source of information for crisis management applications. On one hand, we explore the mapping of our domain model with standard ontologies in the field. On the other hand, we show how the language resources of such a system can be built, starting from an existing domain ontology and a text corpus, by deploying a semisupervised method for ontology lexicalization. As a result, event detection is turned up into an ontology population process, where crowdsourced content is automatically augmented with a shared structured representation, in accordance with the Linked Open Data principles.