Citation

Zuo F, Kurkcu A, Ozbay K, Gao J. Transp. Res. Rec. 2018; 2672(1): 198-208.

Affiliation

C2SMART Center, Department of Civil and Urban Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 2C2SMART Center, Department of Civil & Urban Engineering, Tandon School of Engineering, Center for Urban Science + Progress (CUSP), New York University, Brooklyn, NY 3C2SMART Center (A Tier 1 USDOT UTC), Department of Civil and Urban Engineering & Center for Urban Science & Progress (CUSP), Tandon School of Engineering, New York University, Brooklyn, NY Corresponding Author: Address correspondence to Fan Zuo: fz380@nyu.edu

Copyright

(Copyright © 2018, Transportation Research Board, National Research Council, National Academy of Sciences USA, Publisher SAGE Publishing)

DOI

10.1177/0361198118798736

PMID

unavailable

Abstract

Emergency events affect human security and safety as well as the integrity of the local infrastructure. Emergency response officials are required to make decisions using limited information and time. During emergency events, people post updates to social media networks, such as tweets, containing information about their status, help requests, incident reports, and other useful information. In this research project, the Latent Dirichlet Allocation (LDA) model is used to automatically classify incident-related tweets and incident types using Twitter data. Unlike the previous social media information models proposed in the related literature, the LDA is an unsupervised learning model which can be utilized directly without prior knowledge and preparation for data in order to save time during emergencies. Twitter data including messages and geolocation information during two recent events in New York City, the Chelsea explosion and Hurricane Sandy, are used as two case studies to test the accuracy of the LDA model for extracting incident-related tweets and labeling them by incident type.

RESULTS showed that the model could extract emergency events and classify them for both small and large-scale events, and the model's hyper-parameters can be shared in a similar language environment to save model training time. Furthermore, the list of keywords generated by the model can be used as prior knowledge for emergency event classification and training of supervised classification models such as support vector machine and recurrent neural network.

Language: en