Identifying bursty areas of emergency topics in geotagged tweets using density-based spatiotemporal clustering algorithm

With the increasing popularity of social media, data posted on social media sites are rapidly becoming collective intelligence, which is a term used to refer to new media that is displacing traditional media. In this paper, we focus on geotagged tweets on the Twitter site; such tweets are referred to as georeferenced documents because they include not only a short text message, but also the documents' posting time and location. Geotagged tweets can be used to identify emergency topics such as natural disasters, weather, diseases and other incidents. Therefore, the utilization of geotagged tweets to observe and analyze emergency topics has received much attention recently. In this paper, we propose a new framework for identifying bursty areas of emergency topics using the (ε, τ )-density-based spatiotemporal clustering algorithm. The aim of this study is to develop a new spatiotemporal clustering technique that can extract bursty areas of observed emergency topics such as, natural disasters, weather, and diseases using geotagged tweets. To evaluate the proposed framework, actual crawling geotagged tweets posted on the Twitter site were used. The proposed method could successfully detect bursty areas of an observed an emergency topic that is related to weather in Japan.