The growing availability of geolocated social network contents – so-called Social Media Geographic Information – brought new questions regarding their potential in different situations, from urban mobility planning to crisis scenario. The needs of first-hand feedbacks from affected areas and the social media response during natural disasters have drawn attention of researchers, especially the ones involved in exploiting and interpreting the complex use of SMGI for event detecting and monitoring in time and space. In particular, Twitter, thanks to the possibility of accessing its data through official Application Programming Interfaces, has become the subject of a significant number of studies focused on a great variety of natural disasters (earthquake, hurricanes, floods, fires etc.). This work presents possible geo-statistical and temporal analysis on Twitter posts published during the hurricane Florence emergency that occurred in the United States of America in 2018. The spatial and temporal distribution of geolocated posts has been analysed at different scales, exploring the composition of the SMGI dataset, and identifying at a global scale the areas characterized by a higher level of social media activity. More detailed geostatistical analyses have been performed in order to evaluate the significance of the given geolocated tweets with respect to the natural disaster. The distribution has been explored calculating Nearest Neighbour Indexes. The identification of the most affected areas has been analysed with hot spot analyses and its Getis Ord Gi* index. The results of these analyses and the visual representation of the Kernel Density estimation have then been compared with National Oceanic and Atmospheric Agency (NOAA) and Federal Emergency Management Agency (FEMA) hurricane reports, highlighting the potential for identification of the landfall site through the Twitter dataset and the main issue associated to the influence of densely populated areas on the calculations.
La crescente disponibilità di contenuti geolocalizzati sui social networks – i cosiddetti Social Media Geographic Information – ha posto nuove domande in merito al loro potenziale in diverse situazioni, dalla pianificazione della mobilità urbana fino agli scenari di crisi legati a disastri naturali. La necessità di informazioni immediate relative alle aree direttamente colpite da un’emergenza e il livello di attività registrato sui social media in occasione di disastri naturali hanno richiamato l’attenzione dei ricercatori, interessati a utilizzare e a interpretare la complessità di utilizzo dei SMGI per il rilevamento e il monitoraggio degli eventi nel tempo e nello spazio. In particolare, Twitter, grazie alla possibilità di accedere ai suoi dati attraverso le Application Programming Interface ufficiali, è diventato rapidamente il soggetto di un rilevante numero di studi focalizzati su ogni tipo di disastro naturale (terremoti, uragani, alluvioni, incendi etc.). Questo lavoro presenta alcune possibili analisi geostatistiche e temporali sui post di Twitter pubblicati nel corso dell’emergenza legata all’uragano Florence che ha colpito gli Stati Uniti nel 2018. La distribuzione spaziale e temporale dei post geolocalizzati è stata valutata a scale differenti, in modo da esplorare la composizione del dataset di SMGI e identificare a livello globale le aree caratterizzate da maggiore attività sulla piattaforma di Twitter. Successivamente sono state eseguite analisi geostatistiche più dettagliate per valutare la rappresentatività dei tweets geolocalizzati in rapporto all’evento considerato in una finestra temporale di cinque giorni. Inizialmente, la loro distribuzione è stata valutata attraverso il calcolo del Nearest Neighbour Index. In seguito, è stato calcolato l’indice locale di Getis Ord Gi* per l’analisi degli hot-spot per identificare le aree con attività social più rilevanti. I risultati di queste analisi e le rappresentazioni cartografiche della stima della densità di Kernel sono state in seguito confrontate con i report relativi all’uragano Florence di National Oceanic and Atmospheric Agency (NOAA) e Federal Emergency Management Agency (FEMA), evidenziando il potenziale di identificazione del sito di arrivo sulla terraferma di Florence e le maggiori problematiche associate all’influenza sui calcoli delle aree densamente popolate.
Geolocated Twitter data as a proxy for the analysis of natural disasters : the hurricane Florence case study
Gaspari, Federica
2019/2020
Abstract
The growing availability of geolocated social network contents – so-called Social Media Geographic Information – brought new questions regarding their potential in different situations, from urban mobility planning to crisis scenario. The needs of first-hand feedbacks from affected areas and the social media response during natural disasters have drawn attention of researchers, especially the ones involved in exploiting and interpreting the complex use of SMGI for event detecting and monitoring in time and space. In particular, Twitter, thanks to the possibility of accessing its data through official Application Programming Interfaces, has become the subject of a significant number of studies focused on a great variety of natural disasters (earthquake, hurricanes, floods, fires etc.). This work presents possible geo-statistical and temporal analysis on Twitter posts published during the hurricane Florence emergency that occurred in the United States of America in 2018. The spatial and temporal distribution of geolocated posts has been analysed at different scales, exploring the composition of the SMGI dataset, and identifying at a global scale the areas characterized by a higher level of social media activity. More detailed geostatistical analyses have been performed in order to evaluate the significance of the given geolocated tweets with respect to the natural disaster. The distribution has been explored calculating Nearest Neighbour Indexes. The identification of the most affected areas has been analysed with hot spot analyses and its Getis Ord Gi* index. The results of these analyses and the visual representation of the Kernel Density estimation have then been compared with National Oceanic and Atmospheric Agency (NOAA) and Federal Emergency Management Agency (FEMA) hurricane reports, highlighting the potential for identification of the landfall site through the Twitter dataset and the main issue associated to the influence of densely populated areas on the calculations.| File | Dimensione | Formato | |
|---|---|---|---|
|
2020_10_Gaspari.pdf
accessibile in internet per tutti
Descrizione: Testo della tesi magistrale di Gaspari Federica
Dimensione
7.89 MB
Formato
Adobe PDF
|
7.89 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/166672