Computational models of place are a key component of geospatial information theory and play an increasing role in research ranging from spatial search to transportation studies. One method to arrive at such models is to extract knowledge from user-generated content e.g., from texts, tags, trajectories, pictures, and so forth. Over the past few years, topic modeling techniques have been studied to reveal linguistic patterns that characterize places and their types. In this presentation, I give an overview of some of the approaches that I have taken to linguistically compare and contrast both place instances and place types.
Grant McKenzie is an assistant professor in the Department of Geographical Sciences, affiliate of the Center for Geospatial Information Science, member of the Human Computer Interaction Lab. He holds a PhD in Geography from the University of California, Santa Barbara and a Master of Applied Science degree from the University of Melbourne. Dr. McKenzie’s research interests lie in spatio-temporal data analysis, geovisualization, place-based analytics and the intersection of information technologies and society. Currently, he is exploring computational, data-driven models of human behavior, taking a multi-dimensional approach to investigating the relationship between place & space and the activities people carry out at those places. The foundation of this research involves working with large geosocial, user-contributed and authoritative datasets, exploiting and visualizing spatial, temporal and thematic signatures within the data.