TY - GEN
T1 - Using yelp to find romance in the city
T2 - 3rd ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2017
AU - Rahimi, Sohrab
AU - Andris, Clio
AU - Liu, Xi
N1 - Publisher Copyright:
© 2017 Association for Computing Machinery.
PY - 2017/11/7
Y1 - 2017/11/7
N2 - Romantic relationships are an understudied aspect of cities and the built environment. Yet, restaurants continue to attract couples and augment the landscape with visible signs of affection at a table for two—or more. User-generated content (UGC) of restaurant reviews from online review site Yelp (http://yelp.com) provide text on romantic keywords such as “date”, “love”, “boyfriend”, “wife”, “anniversary”, “family” by geolocated restaurants. We use these to distinguish restaurants and discover features of restaurants associated with various romantic keywords. These features include restaurant ratings and location, as well as comments about the ambiance, food, service, etc. Using data from the Yelp Dataset Challenge in U.S. cities Charlotte, NC, Las Vegas, NM, Phoenix, AZ, and Pittsburgh, PA, we employ different data mining and correlation tools as well as GIS modeling to learn more about what types of romantic relationships use which parts of the city, and how their choices of restaurants differ by relationship stage. We find that families prefer restaurants that are outside of the central business district (CBD), have good service and high-rated food, while couples—married or dating—prefer hot spots with great ambiance for nightlife. We also find that inexpensive food is not associated with romantic dates, and the quality of service also plays a secondary role to a “classy” and “cozy” atmosphere.
AB - Romantic relationships are an understudied aspect of cities and the built environment. Yet, restaurants continue to attract couples and augment the landscape with visible signs of affection at a table for two—or more. User-generated content (UGC) of restaurant reviews from online review site Yelp (http://yelp.com) provide text on romantic keywords such as “date”, “love”, “boyfriend”, “wife”, “anniversary”, “family” by geolocated restaurants. We use these to distinguish restaurants and discover features of restaurants associated with various romantic keywords. These features include restaurant ratings and location, as well as comments about the ambiance, food, service, etc. Using data from the Yelp Dataset Challenge in U.S. cities Charlotte, NC, Las Vegas, NM, Phoenix, AZ, and Pittsburgh, PA, we employ different data mining and correlation tools as well as GIS modeling to learn more about what types of romantic relationships use which parts of the city, and how their choices of restaurants differ by relationship stage. We find that families prefer restaurants that are outside of the central business district (CBD), have good service and high-rated food, while couples—married or dating—prefer hot spots with great ambiance for nightlife. We also find that inexpensive food is not associated with romantic dates, and the quality of service also plays a secondary role to a “classy” and “cozy” atmosphere.
UR - http://www.scopus.com/inward/record.url?scp=85052014331&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85052014331&partnerID=8YFLogxK
U2 - 10.1145/3152178.3152181
DO - 10.1145/3152178.3152181
M3 - Conference contribution
AN - SCOPUS:85052014331
T3 - Proceedings of the 3rd ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2017
BT - Proceedings of the 3rd ACM SIGSPATIAL Workshop on Smart Cities and Urban Analytics, UrbanGIS 2017
PB - Association for Computing Machinery, Inc
Y2 - 7 November 2017 through 10 November 2017
ER -