01659721

Component

https://doi.org/10.1177/0361198118798736

https://doi.org/10.1177/0361198118798736

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.

18-06211

English

pp 198-208

2018

Transportation Research Record: Journal of the Transportation Research Board

Print

Figures (4) ; Maps; References (28) ; Tables (3)

Case studies; Classification; Crowdsourcing; Emergencies; Explosions; Incident management; Social media

Hurricane Sandy, 2012; Twitter

New York (New York)

Data and Information Technology; Security and Emergencies; Transportation (General)

TRIS, TRB, ATRI

Jan 8 2018 11:36AM

• Application of Novel Recovery Techniques to Enhance the Resilience of Transportation Networks
• Assessing Transportation Assets for Vulnerability to Extreme Weather and Other Natural Hazards
• Crisis Communication Patterns in Social Media during Hurricane Sandy
• Developing Priority Index for Managing Utility Disruptions in Urban Areas with Focus on Cascading and Interdependent Effects
• Estimating Choice Models to Quantify the Effect of Herding on the Decision to Evacuate: Application of a Serious Gaming Experimental Setup
• Evaluation of the Traffic Impacts of Mass Evacuation of Halifax: Flood Risk and Dynamic Traffic Microsimulation Modeling
• Exit Choice Behavior of Pedestrians Involving Individuals with Disabilities During Building Evacuations
• Fear in Humans: A Glimpse into the Crowd-Modeling Perspective
• Learning to Build Resilience into Transportation Systems
• Modeling Cyber Attacks at Intelligent Traffic Signals
• Modeling the Effectiveness of Infrastructure and Travel Demand Management Measures to Improve Traffic Congestion during Typhoons
• Road Network Resilience: How to Identify Critical Links Subject to Day-to-Day Disruptions
• Simulating Indoor Evacuation of Pedestrians: The Sensitivity of Predictions to Directional-Choice Calibration Parameters
• Spatially Clustered Autonomous Vehicle Malware: Producing New Urban Geographies of Inequity
• Telecom, Traffic Cones, and the Big One: Identifying Transportation and Communications Emergency Support Workforces and Calculating Their Exposure to Seismic Peak Ground Accelerations
• Transit Information Utilization during an Extreme Weather Event: An Analysis of Smartphone App Data
• Vulnerability of Traffic Control System Under Cyberattacks with Falsified Data