An overview of microblog user geolocation methods

Geographical locations of microblog users are essential for user profiling, event localization and target advertising, to name a few. Automatic identification of user locations from the corresponding microblogs has been explored for decades. This paper presents a survey of existing studies on the problem of microblog user geolocalisation. Specifically, we present a general framework for the geolocalisation of microblog users. In this framework, the location-related information is presented along with the overview of the microblogging platforms. Furthermore, the main steps of the framework are introduced in detail. The state-of-the-art geolocalisation methods are categorized into three classes: the text-based methods, the network-based methods, and the multiview-based methods. Moreover, the advantages and limitations of the existing methods are analyzed theoretically and experimentally. Survey findings conclude that multiview-based methods are superior to the text-based methods as well as the network-based methods. Besides that, existing user geolocalisation methods cannot capture the user's home location change, resulting in the misjudged results. Also, how to locate users from multiple social platforms is relatively unaddressed. Hence, the geolocalization of users across multiple social platforms is one of the problems that deserve further research.