Data-driven discovery of culturally similar urban areas using Google Places

Abstract

Understanding the characteristics of diverse cultural groups worldwide and identifying cultural similarities between their respective regions can yield significant economic and social benefits. However, much of the existing research in this field relies on user behavior data, which poses challenges in scalability and generalization due to the difficulty of obtaining such data. To address this limitation, our work focuses on extracting venue data from Google Places (GP) and introducing a methodology based on the Scenes concept to enrich the GP dataset, enabling the generation of cultural signatures of urban areas. We propose and evaluate an advanced method that enhances venue categories using Scenes Theory, which helps us understand the cultural significance of everyday urban life. Moreover, we compare the Scenes-based approach with two simpler methods that use only venue types and their frequency within the studied areas. We tested all proposed methods in 14 cities worldwide and all US states. Our results indicate that a straightforward approach based on category frequencies can highlight major cultural differences. However, the Scenes Theory-based method offers a better understanding of cultural nuances, aligning with findings supported by survey data. We also explore the impact of varying granularity on the generation of cultural signatures by analyzing three levels of granularity with a hexagonal grid partition. The performed analyses underscore our approach’s societal benefits, such as location recommendations based on cultural criteria and real-time service validation.