Detecting hazardous events from online news and social media

• Main Author: Liu, Zinan
• Other Authors: Mao Kezhi
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Engineering::Computer science and engineering::Computing methodologies::Document and text processing
• Online Access: https://hdl.handle.net/10356/167664
• Institution: Nanyang Technological University

The detection of hazardous events is critical for effective emergency response and risk management. With the widespread use of online news and social media platforms, there is an opportunity to leverage this data source for early warning and situational awareness of hazardous events. This report investigates the potential of using online news and social media data for hazard detection. The report explores the various sources of online data that can be used for hazard detection and analyzes the different methods and techniques used for detecting hazardous events from online data, including natural language processing and machine learning algorithms. Additionally, the report examines the challenges and limitations associated with using online data for hazard detection and discusses potential solutions to address these challenges. The scope of the report is limited to the detection of hazardous events using online news and social media data, and does not cover response and mitigation strategies for these events. The findings of this report can be useful for emergency responders, risk managers, and organizations involved in hazard detection and response. Overall, the report highlights the potential of online data for hazard detection and provides recommendations for future research in this area.