Reading the city through its neighbourhoods: Deep text embeddings of Yelp reviews as a basis for determining similarity and change. (March 2021)

• Record Type: Journal Article
• Authors: Olson, Alexander W.; Calderón-Figueroa, Fernando; Bidian, Olimpia; Silver, Daniel; Sanner, Scott
• Is Part Of: Cities. Volume 110(2021)
• Publication Date: 2021-03
• Subjects: Computational social science -- Urban informatics -- Neighbourhood analysis -- Machine learning -- Text embedding; City planning -- Periodicals; Urban policy -- Periodicals; 711.4
• DOI: 10.1016/j.cities.2020.103045
• Languages: English
• ISSNs: 0264-2751

Abstract

Abstract: This paper develops novel methods for using Yelp reviews as a window into the collective representations of a city and its neighbourhoods. Basing analysis on social media data such as Yelp is a challenging task because review data is highly sparse and direct analysis may fail to uncover hidden trends. To this end, we propose a deep autoencoder approach for embedding the language of neighbourhood-based business reviews into a reduced dimensional space that facilitates similarity comparison of neighbourhoods and their change over time. Our model improves performance in distinguishing real and fake neighbourhood descriptions derived from real reviews, increasing performance in the task from an average accuracy of 0.46 to 0.77. This improvement in performance indicates that this novel application of embedded language analysis permits us to uncover comparative trends in neighbourhood change through the lens of their venues' reviews, providing a computational methodology for reading a city through its neighbourhoods. The resulting toolkit makes it possible to examine a city's current sociological trends in terms of its neighbourhoods' collective identities. Highlights: Deep Autoencoders can be applied to examine urban change through text. Social Media reviews uncover latent change in neighbourhoods. Neighbourhood change is exemplified in online review language.