Authors: Mikael Brunila*, McGill University
Topics: Urban Geography, Geographic Information Science and Systems, Quantitative Methods
Keywords: natural language processing, Bayesian modeling, spatial statistics, sharing economy, short-term rentals
Session Type: Paper
Start / End Time: 1:45 PM / 3:00 PM
Room: Beverly, Sheraton, IM Pei Tower, Terrace Level
Presentation File: No File Uploaded
Airbnb and short-term rentals are raising rents in cities through the use of new technologies and by catering to culturally savvy populations. As a phenomenon of the attention economy, Airbnb is a platform where meaning becomes priced, as efficient and attractive communication is awarded by more bookings. In my presentation, I look at how this capitalization of meaning can be understood by modelling the use of neighbourhood names. Using Natural Language Processing techniques and Bayesian hierarchical models with Intrinsic Auto-Regressive priors, I explore how listings draw upon the value placed on well-known neighbourhood names to promote themselves. On the one hand, I present how to identify neighbourhood names using spatially weighed NLP techniques. On the other hand, I discuss how to use the same names to model the value of place in urban attention economies.