Title: Intelligent and real-time alert model for disaster management based on information retrieval from multiple sources

Authors: Zair Bouzidi; Mourad Amad; Abdelmalek Boudries

Addresses: Faculty of Sciences and Applied Sciences, LIMPAF Laboratory, Computer Science Department, University of Bouira, 10000, Algeria ' Faculty of Sciences and Applied Sciences, LIMPAF Laboratory, Computer Science Department, University of Bouira, 10000, Algeria ' LMA Laboratory, University of Bejaia, 06000, Algeria

Abstract: During the various catastrophic events of recent years, the use of social media to communicate timely information in crisis periods has become a common practice, allowing affected population to quickly publish a considerable amount of disaster information which can help managers making correct and quick decisions. In this paper, we propose a new real-time alert model for the management of natural or anthropogenic disasters. This model is based on a semi-supervised inductive technique to use unlabeled multi-source data, which are often abundant during a crisis event, with less data previously labeled than previous event. We use two sets of real-world crisis data from Facebook and Twitter manually tagged to launch streaming retrieval of relevant content: it is used for evaluating our proposed approach. Preliminary results are satisfactory.

Keywords: disaster management; social neworks; annotated manually messages; multiple sources (Twitter; Facebook;...); social media; neural learning; neural network-based alert system; alert model; intelligent and real-time alert model; knowledge.

DOI: 10.1504/IJAMC.2019.111193

International Journal of Advanced Media and Communication, 2019 Vol.7 No.4, pp.309 - 330

Received: 13 Jun 2019
Accepted: 04 Jun 2020
Published online: 12 Nov 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article