The Geography of Taste: Using Yelp to Study Urban Culture

Abstract

This study aims to put forth a new method to study the sociospatial boundaries by using georeferenced community-authored reviews for restaurants. In this study, we show that food choice, drink choice, and restaurant ambience can be good indicators of socioeconomic status of the ambient population in different neighborhoods. To this end, we use Yelp user reviews to distinguish different neighborhoods in terms of their food purchases and identify resultant boundaries in 10 North American metropolitan areas. This dataset includes restaurant reviews as well as a limited number of user check-ins and rating in those cities. We use Natural Language Processing (NLP) techniques to select a set of potential features pertaining to food, drink and ambience from Yelp user comments for each geolocated restaurant. We then select those features which determine one's choice of restaurant and the rating that he/she provides for that restaurant. After identifying these features, we identify neighborhoods where similar taste is practiced. We show that neighborhoods identified through our method show statistically significant differences based on demographic factors such as income, racial composition, and education. We suggest that this method helps urban planners to understand the social dynamics of contemporary cities in absence of information on service-oriented cultural characteristics of urban communities.

Innovation in hyperlink and social media networks: Comparing connection strategies of innovative companies in hyperlink and social media networks

“…Similarities between these vectors are then calculated separately for the Hyperlink and the Follower Network using the cosine similarity. This is a common approach in natural language processing [ 46 , 47 ]. Further, according to the so-called popularity based filtering, the dictionary is restricted to words with a document frequency of at least 1.5% and at most 65%.…”

Connect the last mile - textual entailment identify efforts in bridging the digital divide

“…Specifically in urban management and governance, researchers have leveraged word-embedding to represent hotel review data for crime prediction (Helderop et al, 2019), used sentiment analysis to retrieve users' taste and cultural backgrounds from Yelp review data (Rahimi et al, 2018), extracted place names from housing advertisement data (Hu et al, 2019). Following a similar trend, the goal of this study is also to enrich the current ISP data from their online textual advertisement.…”

Coproducing spatial information: Exploring government approaches and motivations at the local level

“…The collection of geospatial data is also conducted by harvesting information created for other purposes. For instance, reviews of places or services shared on the internet (Rahimi et al, 2018), opinions or thoughts shared on social media (Zhang & Feick, 2016), or GPS tracks produced during travelling (Attard et al, 2016). Due to the implicit nature of contribution, these processes of harvesting geographic information created by citizens for other purposes are categorized as passive VGI (Craglia et al, 2012;Senaratne et al, 2017), also considered as involuntary VGI or iVGI (Fischer, 2012).…”