During the last ten years, a large body of research extracting and analysing geographic data from social media has developed. We analyse 690 papers across 20 social media platforms, focussing particularly on the method used for extraction of location information. We discuss and compare extraction methods, and consider their accuracy and coverage. While much work has adopted location information in the form of coordinates in message metadata, this approach has very limited coverage in most platforms and reports on posting location rather than message location or the location that the message refers to (geofocus). In contrast, a wide array of other approaches have been developed, with methods that extract place names from message text providing the highest accuracy. Methods that use social media connections also provide good results, but all of the methods have limitations. We also present analysis of the range and frequency of use of different social media platforms, and the wide range of application areas that have been addressed. Drawing on this analysis we present a number of future areas of research that warrant attention in order for this field of research to mature.

Introduction

The potential for social media to provide useful geographic information to either replace or augment traditional methods of data collection has been recognised for some years. In that time, a large number of research efforts have explored this potential with applications including health, disaster management, tourism and recreation, environmental monitoring, crime, civil unrest and marketing. In this paper we provide a systematic literature review of papers across the field, identifying 690 papers within scope, analysing their content in order to compare different aspects of the research and identifying gaps and future research potential, particularly focussing on three aspects. Firstly, we review the different social media platforms that have been used for extracting geodata in the published literature. There is a clear preference for Twitter over other platforms, and we discuss the reasons for this and the potential for the increased use of other platforms to extract data that is not currently being used. Secondly, we explore the methods used to extract location information from social media. While use of metadata geotagging is the most common method, it has a number of limitations, and other methods including text mining, user profiling and different kinds of inference have been developed. We discuss these methods, their use and advantages and disadvantages, analysing accuracy and coverage achieved by each method. Thirdly, we review the impressive array of applications that have been addressed with data extracted from social media, and discuss the dominance of different application areas. Finally, we propose future research directions to cover gaps in the current work, and to enable this research field to reach maturity. The organisation of the paper is as follows. Section 2 discussed previous reviews that have been conducted on social media location data and related areas. Section 3 describes the methodology used for the systematic literature review and presents the research questions. Section 4 provides analysis of the social media platforms used to extract geographic data. Section 5 discusses and compares specific methods of location extraction, providing detailed discussion about the alternative approaches. Section 6 analyses the application domains used in the research papers surveyed and Section 7 discusses future research directions.