Since the 1990's geographers have called for a qualitative GIScience. While several attempts have been made to achieve a qualitative GIS, limiting factors such as data volume and methods have held the realization of such a system back. However, important changes in the last decade have made it possible to achieve this goal. Social media datasets are available for download that contain coordinate metadata and qualitative data about the experiences of individuals. Big data infrastructures make it possible to harvest, store, and find data expressed on specific phenomena researchers wish to study. Natural language processing methods make it possible to understand the context in which a post or group of posts are authored and extract the geospatial insights therein. GIScience has taken notice of these synergies and is beginning to engage with the data and is producing new insights from social media landscapes. In this dissertation, three articles are presented: 1) a method for producing area based topic models from social media; 2) a methodology for geospatial social media exploration and research, and; 3) a software that implements the methods and methodologies of geospatial social media. These three papers make up a body of research that presents a qualitative GIS from data to analysis to output. In the process, the research reflects critically on the ways in which geospatial social media and big data methods in GIScience are created.
Copyright is held by the author.
This thesis may be printed or downloaded for non-commercial research and scholarly purposes.
Supervisor or Senior Supervisor
Thesis advisor: Schuurman, Nadine
Member of collection