ThesisPDF Available

Geolocated Twitter data as a proxy for the analysis of natural disasters: the hurricane Florence case study

Authors:

Abstract and Figures

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.
Content may be subject to copyright.
A preview of the PDF is not available
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Social media data, such as Instagram posts, can be associated with spatial positions. This information can be exploited to perform spatial analyses, such as identifying distribution patterns of points representing the positions of social media users during an emergency or while attending a specific event or exhibition. However, the geolocation provided by Social Media Geographic Information (SMGI) needs to be validated, in order for the spatial data to be used in a meaningful way in subsequent spatial analyses or mapping procedures. In this paper, a case study is presented based on Instagram data collected during the first two months of the Expo Milano 2015 exhibition, where the spatial data have been validated by exploiting the semantic component of the posts.
Article
Full-text available
Social media could be very useful source of data for a people interested in disasters, since it can provide them with on-site information. Posted georeferenced messages and images can help to understand the situation of the area affected by the event. Considering this type of resource as a real-time crowdsource of crisis information, the spatial distribution of geolocated posts related to an event can represent an early indicator of the severity of impact. The aim of this paper is to explore the spatial distribution of Twitter posts related to hurricane Michael, occurred in the USA in 2018 and to analyse their potential in providing a fast insight about the event impact. Kernel density estimation has been applied to explore the spatial distribution of Twitter posts, after which Hot Spot analysis has been performed in order to analyse the spatiotemporal distribution of the data. Hot Spot analysis has shown to be the most comprehensive analysis, detecting the area of high impact. The Kernel density map has shown to be useful as well.
Article
Full-text available
A growing social science literature has used Twitter and Facebook to study political and social phenomena including for election forecasting and tracking political conversations. This research note uses a nationally representative probability sample of the British population to examine how Twitter and Facebook users differ from the general population in terms of demographics, political attitudes and political behaviour. We find that Twitter and Facebook users differ substantially from the general population on many politically relevant dimensions including vote choice, turnout, age, gender, and education. On average social media users are younger and better educated than non-users, and they are more liberal and pay more attention to politics. Despite paying more attention to politics, social media users are less likely to vote than non-users, but they are more likely to support the left leaning Labour Party when they do vote. However, we show that these apparent differences mostly arise due to the demographic composition of social media users. After controlling for age, gender, and education, no statistically significant differences arise between social media users and non-users on political attention, values or political behaviour.
Article
Full-text available
Hundreds of papers have been published using Twitter data, but no previous paper reports the digital divide among Twitter users. British Twitter users are younger, wealthier, and better educated than other Internet users, who in turn are younger, wealthier, and better educated than the off-line British population. American Twitter users are also younger and wealthier than the rest of the population, but they are not better educated. Twitter users are disproportionately members of elites in both countries. Twitter users also differ from other groups in their online activities and their attitudes. These biases and differences have important implications for research based on Twitter data. The unrepresentative characteristics of Twitter users suggest that Twitter data are not suitable for research where representativeness is important, such as forecasting elections or gaining insight into attitudes, sentiments, or activities of large populations. In general, Twitter data seem to be more suitable for corporate use than for social science research.
Chapter
Full-text available
This contribution introduces the concept of Social Media Geographic Information (SMGI) as a specific type of Volunteered Geographic Information (VGI). Unlike other kind of VGI, which may originate from geographic measurements crowdsourcing, SMGI brings in addition a special potential for it may express community perceptions, interests, needs, and behaviors. Hence, SMGI may represent an unprecedented resource for expressing pluralism in such domains as spatial planning, where it may convey the community collective preferences contributing to enrich knowledge able to inform design and decision making. In the light of these assumptions, the main issues relevant for SMGI collection and analytics are presented from the perspective of the spatial planning and governance domain, and a framework for the SMGI analytics in planning, design, and decision making is proposed.
Article
Disasters are natural catastrophic events that cause damage to property and loss of lives. Highly-reliable in-situ location information is critical for rescue efforts during and after disasters, but often such information is not easy or even possible to obtain. The recent technological advancements along with the volunteerism opportunities create the possibility for obtaining the most needed information through citizens via online applications. The paper investigates the role of volunteer crowdsourcing, including its key attributes and relevant technologies, in disaster risk reduction. This study adopts the systematic literature review technique as the methodological approach. The results reveal three major application areas, where the data collection is undertaken through volunteer crowdsourcing—i.e., marketing, communication, disasters. The findings point out to a trend of increasing focus on volunteer crowdsourcing in the disaster risk reduction literature between 2006 and 2018. The study suggests that the adoption of volunteer crowdsourcing systems into practice would assist policymakers and disaster risk managers to make informed decisions before, during and after disasters—hence, could help in reducing risks.
Article
Introduced in this paper is a family of statistics, G, that can be used as a measure of spatial association in a number of circumstances. The basic statistic is derived, its properties are identified, and its advantages explained. Several of the G statistics make it possible to evaluate the spatial association of a variable within a specified distance of a single point. A comparison is made between a general G statistic andMoran’s I for similar hypothetical and empirical conditions. The empiricalwork includes studies of sudden infant death syndrome by county in North Carolina and dwelling unit prices in metropolitan San Diego by zip-code districts. Results indicate that G statistics should be used in conjunction with I in order to identify characteristics of patterns not revealed by the I statistic alone and, specifically, the Gi and G∗ i statistics enable us to detect local “pockets” of dependence that may not show up when using global statistics.