User-driven geo-temporal density-based exploration of periodic and not periodic events reported in social networks - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Journal Articles Information Sciences Year : 2016

User-driven geo-temporal density-based exploration of periodic and not periodic events reported in social networks

Abstract

In this paper we propose a procedure consisting of a first collection phase of social net- work messages, a subsequent user query selection, and finally a clustering phase, de- fined by extending the density-based DBSCAN algorithm, for performing a geographic and temporal exploration of a collection of items, in order to reveal and map their latent spatio-temporal structure. Specifically, both several geo-temporal distance measures and a density-based geo-temporal clustering algorithm are proposed. The approach can be applied to social messages containing an explicit geographic and temporal location. The algorithm usage is exemplified to identify geographic regions where many geotagged Twitter messages about an event of interest have been created, possibly in the same time period in the case of non-periodic events (aperiodic events), or at regular timestamps in the case of periodic events. This allows discovering the spatio-temporal periodic and aperiodic characteristics of events occurring in specific geographic areas, and thus increasing the awareness of decision makers who are in charge of territorial planning. Several case studies are used to illustrate the proposed procedure.
Fichier principal
Vignette du fichier
geotemporalExplorationTwitter.pdf (5.59 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-01275619 , version 1 (17-02-2016)

Identifiers

Cite

Paolo Arcaini, Gloria Bordogna, Dino Ienco, Simone Sterlacchini. User-driven geo-temporal density-based exploration of periodic and not periodic events reported in social networks. Information Sciences, 2016, 340, pp.122-143. ⟨10.1016/j.ins.2016.01.014⟩. ⟨lirmm-01275619⟩
377 View
429 Download

Altmetric

Share

Gmail Facebook X LinkedIn More