As part of our “Research Bites” series, in which we ask data science researchers to spend five minutes telling us in their own words about their work, and opportunities for practical applicability in the context of sustainable development or humanitarian action, today we hear from researchers Stefano Cresci, Maurizio Tesconi and Andrea Marchetti from The Institute of Informatics and Telematics of CNR.
EARS (Earthquake Alert and Report System): a Real Time Decision Support System for Earthquake Crisis Management
Put simply, if you feel a tremor you are likely to post about it online. When this happens en masse then the trends can be used to monitor earthquakes in real-time. The larger the tremor, the more people talk about it online. The Earthquake Alert and Report System (EARS) picks up on that online chatter and automates emails and tweets on detected events. This information can be used by government agencies to help ensure prompt response. This research study used tweets and focused on Italy, during a time of seismic activity.
The full research paper can be accessed online here.
1. Tell us about your research paper in two sentences
We describe a decision support system for the detection and the damage assessment of earthquakes with social media data. Our system analyzes the messages shared in real-time on Twitter with data mining and natural language processing techniques in order to assess the consequences of a seismic event on both population and infrastructures.
2. Why do your findings matter?
The proposed system can enhance current earthquake emergency management procedures by improving situational awareness thus reducing response times and allowing to concentrate rescue teams where they are actually needed. This could help mitigate the effect of earthquakes and reduce losses in terms of both human lives and economic impact.
3. How could this research be put into practice?
The EARS system can be integrated with other already established systems such as the ShakeMaps, Did You Feel It? (DYFI?) and PAGER systems. We believe that the best results can be achieved by combining the strengths of all these systems together.
4. Why did you select this topic to research?
Big Data has already been employed in many ways with the goal of improving human life quality. Previous works in fields such as epidemiology and syndromic surveillance demonstrated how this huge amount of information can be exploited to better face medical emergencies. We believe that the same applies to the case of natural emergencies. Real-time analysis of big data by means of data mining techniques can help take a crucial step forward for novel emergency management systems.
The researchers will be on hand to answer questions in the comments section below, so we invite practitioners from the development or humanitarian sectors to join the discussion!