Leveraging Twitter to gauge evacuation compliance: Spatiotemporal analysis of Hurricane Matthew

Abstract

Hurricane Matthew was the deadliest Atlantic storm since Katrina in 2005 and prompted one of the largest recent hurricane evacuations along the Southeastern coast of the United States. The storm and its projected landfall triggered a massive social media reaction. Using Twitter data, this paper examines the spatiotemporal variability in social media response and develops a novel approach to leverage geotagged tweets to assess the evacuation responses of residents. The approach involves the retrieval of tweets from the Twitter Stream, the creation and filtering of different datasets, and the statistical and spatial processing and treatment to extract, plot and map the results. As expected, peak Twitter response was reached during the pre-impact and preparedness phase, and decreased abruptly after the passage of the storm. A comparison between two time periods—pre-evacuation (October 2th-4th) and post-evacuation (October 7th-9th)—indicates that 54% of Twitter users moved away from the coast to a safer location, with observed differences by state on the timing of the evacuation. A specific sub-state analysis of South Carolina illustrated overall compliance with evacuation orders and detailed information on the timing of departure from the coast as well as the destination location. These findings advance the use of big data and citizen-as-sensor approaches for public safety issues, providing an effective and near real-time alternative for measuring compliance with evacuation orders.

Using Twitter to Analyze the Effect of Hurricanes on Human Mobility Patterns

“…In addition to this, tweets posted after landfall for Hurricane Harvey suggest that they relate to the impact and recovery stage. The two peaks found in North/South Carolina can potentially be attributed to the evacuation order on 4 October 2016 (local peak) and landfall on 8 October 2016 (global peak) [11], which gives a distinct pattern compared to the other two study areas in Houston and Miami-Dade with only one distinct peak. The latter could be explained by the fact that no evacuation orders were given for Houston [52], and that no mandatory but only selected voluntary evacuations were conducted for Miami-Dade During Hurricane Matthew, two event-related hashtags (#hurricanematthew, #matthew) were found among the top ten hashtags in Miami-Dade County, but none before and after.…”

“…As expected, the frequency of disaster related tweets is highest in the spatial proximity of a disaster [8,9].Related work on movement analysis focuses primarily on the effects of crisis events on a larger scale and longer-term movements. One study, for example, explored evacuation patterns by leveraging user location information from tweets posted in the hours prior and concurrent to Hurricane Matthew in 2016 [10], and another study used Twitter data to estimate the percentage of evacuees during the same hurricane [11]. Tweets were also used to identify refugee migration patterns from the Middle East and Northern Africa to Europe during the initial surge of refugees aiming for Europe in 2015 [12].Despite such analysis, the effect of natural disasters on local mobility patterns (e.g., for the population remaining in the affected regions during such an event), is less explored.…”

“…Related work on movement analysis focuses primarily on the effects of crisis events on a larger scale and longer-term movements. One study, for example, explored evacuation patterns by leveraging user location information from tweets posted in the hours prior and concurrent to Hurricane Matthew in 2016 [10], and another study used Twitter data to estimate the percentage of evacuees during the same hurricane [11]. Tweets were also used to identify refugee migration patterns from the Middle East and Northern Africa to Europe during the initial surge of refugees aiming for Europe in 2015 [12].…”

Utilizing Geo-tagged Tweets to Understand Evacuation Dynamics during Emergencies

“…Real-time tools for relevant tweet discovery and their spatial visualization during emergency situations were developed in [6,7]. Martin et al [30] applied the techniques in [6,7] to a case study of hurricane Mathew to evaluate the potential for social media to assist in the quantification of evacuation participation and compliance by residents. Next, we describe the Hurricane Sandy Twitter dataset used in this study.…”

Patterns of population displacement during mega-fires in California detected using Facebook Disaster Maps

“…Studies and actual practices have been carried out using the geotagged Tweets and Flickr picture uploads to track and reveal the change and distribution of population during natural disasters and public safety crises (3)(4)(5)(6)(7)(8). These successful applications also motivated the leading social media platforms to develop their official crisis response tools.…”