文摘
When an earthquake occurs, a huge amount of data is generated by social media users. Social networks play therefore a fundamental role in the development of decision support systems that could help both government and citizens. From user-generated contents, the information about an occurring emergency could be acquired and exploited to understand the critical event and its evolution over time. On the other side, the social interactions among users can be exploited as a dissemination gate to make people informed. In this paper, we present a decision support system for earthquake management based on machine learning and natural language processing to effectively extract and organize knowledge from online social media data. The proposed system, on a real Twitter dataset, has shown significant results for identifying messages related to (real) earthquakes and critical tremors, highlighting those posts provided by spontaneous users and containing any actionable knowledge about damages, magnitude, location and time references.