This study analyzes Location-Based Social Network (LBSN) data from Foursquare and Google Places to model interest networks (iNETs), revealing similar urban behavior patterns despite differences in data structure.

Paper  

CityHood is an interactive, explainable recommendation system that suggests cities and neighborhoods based on user interests. It uses Google Places reviews, geographic, socio-demographic, political, and cultural data to generate personalized recommendations at city (CBSA) and neighborhood (ZIP code) levels. The system employs LIME for explainability and provides natural-language justifications, allowing users to explore recommendations via a visual interface. By combining spatial, cultural, and interest-based analysis, CityHood enhances transparency in travel recommendations.

Paper   Interactive-tool

This study proposes a method to analyze cultural similarities between urban areas using Google Places data and the Scenes concept, avoiding reliance on user behavior data. Case studies in Curitiba, Brazil, and Chicago, USA, show the approach can identify cultural clusters, supporting applications like culturally informed location recommendations. The method is scalable and adaptable to different city sizes.

Paper 

By exploring a public large-scale dataset from Yelp, we show the potential of our approach for considering structural connectedness in predicting neighbourhood attributes, specifically to predict local culture. Results are promising from a substantive and methodologically point of view. 

Paper 

Paper   -   Extra Material

We focus on location-based social network platforms and present solutions to data integration based on physical venues, groups of users interacting with them, and activities performed in those venues. Besides, we also propose an ontology (Social Media Integration Ontology - SMIO) that provides a target data model into which data from multiple sources can be mapped with more precise, shared semantics. Our proposed approaches and ontology can help to enhance the variety of data that describes a venue or group and foster research into urban societies.

Paper 

Our study has sought to advance the literature on neighbourhood change and functional explanation by demonstrating how functional explanation can be revived in the context of big data. We adapted the classical model of functional explanation formulated by Stinchcombe to study neighbourhood change with Yelp data.

Paper - dataset 

 This paper elaborates a multi-model approach to studying how local scenes change. Our overall goal is to point toward new research arcs on change models of scenes, and to give some clear examples and directions for how to think about and collect data to understand what makes some scenes change, others not, why, and in what directions.

Paper

This paper seeks to advance neighbourhood change research and complexity theories of cities by developing and exploring a Markov model of socio-spatial neighbourhood evolution in Toronto, Canada.

Paper  -  citation

This paper focuses on the venue integration problem through categories of venues. We propose an ontology to support the integration of venues across different data sources in this context. This is an important building block for integrating multiple datasets to study urban issues.

Paper 

CityHood is an interactive, explainable recommendation system that suggests cities and neighborhoods based on user interests.

h3-cities utilizes OpenStreetMap and Uber's Hexagonal Hierarchical Geospatial Indexing System to subdivide a particular region into hexagons of various sizes. This allows for the division of any city with available OpenStreetMap data, providing a consistent, multi-scalar framework for urban analysis

Improved version of the tool Google Places Enricher, easier to use by non-techy people

This tool makes it easy to get data from Google Places API from any geographical area. It also helps to enrich it with other categories of interest – including from different systems (Yelp categories are available by default).