Unifying points of interest taxonomies: mapping OpenStreetMap tags to the Foursquare category system

2025/11/17 by Lilou Soulas, Soulas, Lilou, Lorenzo Lucchini +13
Engineering · Social Sciences · #FOS: Computer and information sciences #FOS: Physical sciences #Geographic Information Systems Studies #Human Mobility and Location-Based Analysis #Physics and Society (physics.soc-ph) #Smart Cities and Technologies #Social and Information Networks (cs.SI)

paper · pdf · doi:10.48550/arxiv.2511.13369

openalex publication_date 2025/11/17 · openalex created_date 2025/11/19 · openalex updated_date 2026/07/28

Abstract

The heterogeneity of Point of Interest (POI) taxonomies is a persistent challenge for the integration of urban datasets and the development of location-based services. OpenStreetMap (OSM) adopts a flexible, community-driven tagging system, while Foursquare (FS) relies on a curated hierarchical structure. Here we present an openly available benchmark and mapping framework that aligns OSM tags with the FS taxonomy. This resource integrates the richness of community-driven OSM data with the hierarchical structure of FS, enabling reproducible and interoperable urban analytics. The dataset is complemented by an evaluation of embedding and LLM-based alignment strategies and a pipeline that supports scalable updates as OSM evolves. Together, these elements provide both a robust reference resource and a practical tool for the community. Our approach is structured around three components: the construction of a manually curated benchmark as a gold standard, the evaluation of pretrained text embedding models for semantic alignment between OSM tags and FS categories, and an LLM-based refinement stage that enhances robustness and adaptability. The proposed methodology provides a scalable and reproducible solution for taxonomy unification, with direct applications to urban analytics, mobility studies, and smart city services.

Citations

• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering
• Ontology Matching with Large Language Models and Prioritized Depth-First Search
• Bias in Large Language Models: Origin, Evaluation, and Mitigation
• Fine-tuning Large Language Models for Entity Matching
• The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints
• Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
• Mixing Individual and Collective Behaviours to Predict Out-of-Routine Mobility
• Job loss disrupts individuals' mobility and their exploratory patterns
• Generative Judge for Evaluating Alignment
• Large Language Models Are Not Robust Multiple Choice Selectors
• OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts
• MPNet: Masked and Permuted Pre-training for Language Understanding
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• TinyBERT: Distilling BERT for Natural Language Understanding
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• A systematic analysis of performance measures for classification tasks
• An introduction to ROC analysis

Related

• World-POI: Global Point-of-Interest Data Enriched from Foursquare and OpenStreetMap as Tabular and Graph Data
• A Deep Dive into OpenStreetMap Research Since its Inception (2008-2024): Contributors, Topics, and Future Trends
• Data coverage, richness, and quality of OpenStreetMap for special interest tags: wayside crosses -- a case study
• ML Updates for OpenStreetMap: Analysis of Research Gaps and Future Directions
• Collaborative toponyms in OpenStreetMap: an open-source framework to investigate the relationship with intrinsic quality parameters