Early detection of emergency events from social media: a new text clustering approach

Emergency events require early detection, quick response, and accurate recovery. In the era of big data, social media users can be seen as social sensors to monitor real-time emergency events. This paper proposed an integrated approach to detect all four kinds of emergency events early, including natural disasters, man-made accidents, public health events, and social security events. First, the BERT-Att-BiLSTM model is used to detect emergency-related posts from massive and irrelevant data. Then, the 3 W attribute information (what, where, and when) of the emergency event is extracted. With the 3 W attribute information, we create an unsupervised dynamical event clustering algorithm based on text similarity and combine it with the supervised logistical regression model to cluster posts into different events. Experiments on Sina Weibo data demonstrate the superiority of the proposed framework. Case studies on some real emergency events show that the proposed framework has good performance and high timeliness. Practical applications of the framework are also discussed, followed by future directions for improvement.