Early detection of emergency events from social media: A new text clustering approach Lida Huang (
[email protected] ) Tsinghua University https://orcid.org/0000-0002-2663-6221 Panpan Shi Tsinghua-Gsafety Joint Institute of Public Safety Research, Gsafety Company Haichao Zhu Tsinghua-Gsafety Joint Institute of Public Safety and Emergency Technology Research, Gsafety Company Tao Chen Tsinghua University Research Article Keywords: Emergency event, early detection, social media, text clustering, Bi-LSTM, BERT Posted Date: April 12th, 2021 DOI: https://doi.org/10.21203/rs.3.rs-322787/v1 License: This work is licensed under a Creative Commons Attribution 4.0 International License. Read Full License Early detection of emergency events from social media: A new text clustering approach Lida Huanga, Panpan Shib, Haichao Zhu, Tao Chena* a Institute of Public Safety Research, Department of Engineering Physics, Tsinghua University, Beijing, China, 100084 b Tsinghua-Gsafety Joint Institute of Public Safety and Emergency Technology Research, Gsafety Company, Beijing, China, 100094 Correspondence information: Tao Chen, Institute of Public Safety Research, Department of Engineering Physics, Tsinghua University, Beijing, China, 100084,
[email protected], 86-010-62796981 All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Lida Huang, Panpan Shi and Haichao Zhu. The first draft of the manuscript was written by Lida Huang and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript. 1 Abstract Emergency events need early detection, quick response, and accuracy recover. In the era of big data, social media users can be seen as social sensors to monitor real time emergency events.