PMID- 30979067 OWN - NLM STAT- MEDLINE DCOM- 20190809 LR - 20200225 IS - 1424-8220 (Electronic) IS - 1424-8220 (Linking) VI - 19 IP - 7 DP - 2019 Apr 11 TI - Using Twitter Data to Monitor Natural Disaster Social Dynamics: A Recurrent Neural Network Approach with Word Embeddings and Kernel Density Estimation. LID - 10.3390/s19071746 [doi] LID - 1746 AB - In recent years, Online Social Networks (OSNs) have received a great deal of attention for their potential use in the spatial and temporal modeling of events owing to the information that can be extracted from these platforms. Within this context, one of the most latent applications is the monitoring of natural disasters. Vital information posted by OSN users can contribute to relief efforts during and after a catastrophe. Although it is possible to retrieve data from OSNs using embedded geographic information provided by GPS systems, this feature is disabled by default in most cases. An alternative solution is to geoparse specific locations using language models based on Named Entity Recognition (NER) techniques. In this work, a sensor that uses Twitter is proposed to monitor natural disasters. The approach is intended to sense data by detecting toponyms (named places written within the text) in tweets with event-related information, e.g., a collapsed building on a specific avenue or the location at which a person was last seen. The proposed approach is carried out by transforming tokenized tweets into word embeddings: a rich linguistic and contextual vector representation of textual corpora. Pre-labeled word embeddings are employed to train a Recurrent Neural Network variant, known as a Bidirectional Long Short-Term Memory (biLSTM) network, that is capable of dealing with sequential data by analyzing information in both directions of a word (past and future entries). Moreover, a Conditional Random Field (CRF) output layer, which aims to maximize the transition from one NER tag to another, is used to increase the classification accuracy. The resulting labeled words are joined to coherently form a toponym, which is geocoded and scored by a Kernel Density Estimation function. At the end of the process, the scored data are presented graphically to depict areas in which the majority of tweets reporting topics related to a natural disaster are concentrated. A case study on Mexico's 2017 Earthquake is presented, and the data extracted during and after the event are reported. FAU - Hernandez-Suarez, Aldo AU - Hernandez-Suarez A AUID- ORCID: 0000-0002-4867-2717 AD - Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico. ahernandezs1325@alumno.ipn.mx. FAU - Sanchez-Perez, Gabriel AU - Sanchez-Perez G AUID- ORCID: 0000-0002-4867-2717 AD - Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico. caaann@gmail.com. FAU - Toscano-Medina, Karina AU - Toscano-Medina K AUID- ORCID: 0000-0002-4867-2717 AD - Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico. ljaviergv@hotmail.com. FAU - Perez-Meana, Hector AU - Perez-Meana H AUID- ORCID: 0000-0002-4867-2717 AD - Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico. ljaviergv@gmail.com. FAU - Portillo-Portillo, Jose AU - Portillo-Portillo J AUID- ORCID: 0000-0002-4867-2717 AD - Instituto Politecnico Nacional, ESIME Culhuacan, Mexico City 04440, Mexico. ljgv.69@gmail.com. FAU - And Luis, Victor Sanchez AU - And Luis VS AUID- ORCID: 0000-0001-7573-6272 AD - Department of Computer Science, University of Warwick, Coventry CV4 7AL, UK. v.f.Sanchez-Silva@warwick.ac.uk. AD - Group of Analysis, Security and Systems (GASS), Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), Calle Profesor Jose Garcia Santesmases, 9, Ciudad Universitaria, 28040 Madrid, Spain. v.f.Sanchez-Silva@warwick.ac.uk. FAU - Javier Garcia Villalba, Luis AU - Javier Garcia Villalba L AD - Group of Analysis, Security and Systems (GASS), Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), Calle Profesor Jose Garcia Santesmases, 9, Ciudad Universitaria, 28040 Madrid, Spain. javiergv@fdi.ucm.es. LA - eng PT - Journal Article DEP - 20190411 PL - Switzerland TA - Sensors (Basel) JT - Sensors (Basel, Switzerland) JID - 101204366 MH - Algorithms MH - *Geographic Information Systems MH - Humans MH - Internet MH - Machine Learning MH - Mexico MH - Natural Disasters/*prevention & control MH - Natural Language Processing MH - Neural Networks, Computer MH - *Social Media PMC - PMC6484392 OTO - NOTNLM OT - CRF OT - LSTM OT - data mining OT - geocoding OT - geoparsing OT - twitter OT - word2vec COIS- The authors declare no conflict of interest. EDAT- 2019/04/14 06:00 MHDA- 2019/08/10 06:00 PMCR- 2019/04/01 CRDT- 2019/04/14 06:00 PHST- 2019/03/03 00:00 [received] PHST- 2019/03/29 00:00 [revised] PHST- 2019/03/29 00:00 [accepted] PHST- 2019/04/14 06:00 [entrez] PHST- 2019/04/14 06:00 [pubmed] PHST- 2019/08/10 06:00 [medline] PHST- 2019/04/01 00:00 [pmc-release] AID - s19071746 [pii] AID - sensors-19-01746 [pii] AID - 10.3390/s19071746 [doi] PST - epublish SO - Sensors (Basel). 2019 Apr 11;19(7):1746. doi: 10.3390/s19071746.