Learning Early Detection of Emergencies from Word Usage Patterns on Social Media - Information Technology in Disaster Risk Reduction
Conference Papers Year : 2023

Learning Early Detection of Emergencies from Word Usage Patterns on Social Media

Abstract

In the early stages of an emergency, information extracted from social media can support crisis response with evidence-based content. In order to capture this evidence, the events of interest must be first promptly detected. An automated detection system is able to activate other tasks, such as preemptive data processing for extracting event-related information. In this paper, we extend the human-in-the-loop approach in our previous work, TriggerCit, with a machine-learning-based event detection system trained on word count time series and coupled with an automated lexicon building algorithm. We design this framework in a language-agnostic fashion. In this way, the system can be deployed to any language without substantial effort. We evaluate the capacity of the proposed work against authoritative flood data for Nepal recorded over two years.
Embargoed file
Embargoed file
1 3 5
Year Month Jours
Avant la publication
Thursday, January 1, 2026
Embargoed file
Thursday, January 1, 2026
Please log in to request access to the document

Dates and versions

hal-04680532 , version 1 (28-08-2024)

Licence

Identifiers

Cite

Carlo A. Bono, Mehmet Oğuz Mülâyim, Barbara Pernici. Learning Early Detection of Emergencies from Word Usage Patterns on Social Media. 7th International Conference on Information Technology in Disaster Risk Reduction (ITDRR), Oct 2022, Krisitansand, Norway. pp.308-323, ⟨10.1007/978-3-031-34207-3_20⟩. ⟨hal-04680532⟩
30 View
1 Download

Altmetric

Share

More