A Method for Developing Seismic Intensity Maps from Twitter Data

Abstract

Aim of this article, is to present a methodology for extracting macroseismic intensity information and producing seismic intensity maps from VGI (volunteered geographic information). As a VGI source for obtaining and assessing macroseismic observations, the authors chose twitter. Our methodology is validated in two recent earthquakes occurred in Greece: the January 26, 2014 ML = 5.8 in Kefallinia, and the November 17, 2014 ML = 5.2 in Evoikos. Twitter data published within the first 6 h, 12 h, 24 h and 48 h after the earthquake occurrence were analyzed to develop seismic intensity maps. Those maps were evaluated through intensity maps for the same earthquakes, published by international institutes. Evaluation results provide a strong empiric evidence for the credibility of our methodology, the accuracy of the produced seismic intensity maps and accentuate VGI, generated by twitter, as an adequate alternative source for collecting macroseismic information.

Developing Seismic Intensity Maps From Twitter Data; The Case Study of Lesvos, Greece 2017 Earthquake: Assessments, Improvements and Enrichments on the Methodology

“…Various text-patterns that had been identified in previously published research (Arapostathis et al 2015(Arapostathis et al , 2016 are applied automatically, improving thus the process in terms of speed. Moreover, during the analysis, new text-patterns are identified and added to the table (Table I).…”

“…In 2016, a different approach for creating seismic intensity maps was introduced, based on the extraction of macroseismic observations from social media (Arapostathis et al 2016). Moreover, Kropivnitskaya et al (2016) presented a hybrid research for the creation of seismic intensity maps, using both physical and social sensors.…”

Social Network Users Create Seismic Intensity Maps: An Automatic Approach of the Methodology

“…Apart from the tweets, a second dataset, consisted of word patterns that were linked to seismic intensity values of the European Macroseismic Scale (EMS98) was used. As already mentioned, the word patterns had been identified during previous research [4][5][6], had been also justified according to the official EMS98 description [19] and are displayed in Table 1. In cases that a certain word pattern could fit in a range of values, instead of one certain (i.e.…”

“…Additionally, the author, during the latest years, researched on manipulating exclusively social media information for generating seismic intensity maps, emerging thus the usefulness of the enormous, in terms of quantity, dynamic content that is constantly generated [3,4,5]. The output of author's previous research led, among others, to the identification of word patterns that can be used to classify the texts of social media posts according to the values of the macroseismic intensity scale.…”