Abstract
Timely and accurate information about ongoing events are crucial for relief organizations seeking to effectively respond to disasters. Recently, social media platforms, especially Twitter, have gained traction as a novel source of information on disaster events. Unfortunately, geographical information is rarely attached to tweets, which hinders the use of Twitter for geographical applications. As a solution, geoparsing algorithms extract and can locate geographical locations referenced in a tweet’s text. This paper describes TAGGS, a new algorithm that enhances location disambiguation by employing both metadata and the contextual spatial information of groups of tweets referencing the same location regarding a specific disaster type. Validation demonstrated that TAGGS approximately attains a recall of 0.82 and precision of 0.91. Without lowering precision, this roughly doubles the number of correctly found administrative subdivisions and cities, towns, and villages as compared to individual geoparsing. We applied TAGGS to 55.1 million flood-related tweets in 12 languages, collected over 3 years. We found 19.2 million tweets mentioning one or more flood locations, which can be towns (11.2 million), administrative subdivisions (5.1 million), or countries (4.6 million). In the future, TAGGS could form the basis for a global event detection system.
Highlights
Each year, natural disasters affect roughly one million people, causing thousands of deaths and tens of billions of US dollars in damages (UNISDR 2015)
The aim of this study is to develop a global geoparsing algorithm for tweets without assuming a priori knowledge about an event so that the algorithm can be employed for event detection
The results underscored that relatively small countries, such as the Philippines (PHL) and Venezuela (VEN), generated a significant number of flood tweets within their respective groups. These findings suggest that flood events, and not just the size of the population or the Twitter user base, are responsible for the high number of tweets during the investigated time period
Summary
Natural disasters affect roughly one million people, causing thousands of deaths and tens of billions of US dollars in damages (UNISDR 2015). The Twitter posts (Btweets^) that are sent out by millions of users around the globe hold great potential in disaster management (Carley et al 2016; Jongman et al 2015; Sakaki et al 2010) When correctly analyzed, they can improve the detection of disasters (Ghahremanlou et al 2014) and provide valuable information about the societal impacts of ongoing disaster events (Fohringer et al 2015; Gao et al 2011; Jongman et al 2015). Examples of such applications include detection of flood events (Jongman et al 2015) and earthquake disasters (Crooks et al 2013; Sakaki et al 2010)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
