Social Construction of Urban Space: Using LLMs to Identify Neighborhood Boundaries From Craigslist Ads

2026-06-25 · Source: Paper Index on ACL Anthology · Field: Science & Research — Social Sciences & Behavioral Studies, Artificial Intelligence & Machine Learning · Depth: Expert, medium

Summary

An analysis of Chicago Craigslist rental advertisements from 2018 to 2024 reveals how urban space is socially constructed through language, often diverging from institutional boundaries. Researchers used manual and large language model (LLM) annotation to classify unstructured listings by neighborhood. Geospatial analysis identified three patterns: properties with conflicting neighborhood designations, border properties with valid claims to adjacent areas, and "reputation laundering" where listings claim association with distant, desirable neighborhoods. Topic modeling further showed that listings further from neighborhood centers emphasize different amenities than centrally-located units. This study demonstrates how natural language processing techniques uncover contested definitions of urban spaces that traditional methods often miss.

Key takeaway

For urban planners or real estate analysts seeking to understand dynamic urban boundaries, traditional methods often miss nuanced social constructions of neighborhoods. You should consider integrating LLM-driven natural language processing and geospatial analysis of rental listings. This approach offers a powerful tool to identify discrepancies like "reputation laundering" or contested border claims, informing more accurate planning decisions and market strategies.

Key insights

LLMs and NLP reveal contested urban space definitions from rental listings, uncovering boundary mismatches and "reputation laundering."

Principles

• Urban space definitions are socially constructed through language.
• Listing agents characterize neighborhoods in ways that diverge from institutional boundaries.
• Amenities emphasized in listings correlate with spatial positioning.

Method

Classify unstructured Craigslist rental listings (2018-2024) by neighborhood using manual and LLM annotation, followed by geospatial and topic modeling analysis.

In practice

• Identify conflicting neighborhood designations.
• Detect "reputation laundering" in real estate.
• Analyze amenity emphasis based on location.

Topics

• Natural Language Processing
• Large Language Models
• Urban Geography
• Neighborhood Analysis
• Computational Social Science
• Real Estate Data

Best for: NLP Engineer, AI Scientist, Research Scientist

Related on AIssential

• SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models — LLMs encode structured spatial gender biases that exceed real-world distributions, impacting urban planning applications.
• Advancing E-commerce Merchants Telemarketing with Synthetic Data-Driven LLMs — Synthetic data generation can significantly improve LLM performance in complex, strategy-driven telemarketing dialogues.
• Graph-Enhanced Large Language Models for Spatial Search — LLMs require graph-enhanced reasoning to overcome spatial limitations for real-world applications.
• ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing — ChatPlanner integrates fine-tuned LLMs and RAG to enable personalized public transit routing by interpreting natural language preferences.
• Discovery of Legal Patterns in Civil Petitions via LLM-Based Fact Extraction and Density Clustering — LLM-based fact extraction significantly improves legal document clustering by reducing noise and enhancing semantic coherence.
• Are LLMs Ready for Anti-Pattern Detection in Microservice Architectures? — LLMs complement static analysis for microservice anti-pattern detection, excelling with semantic cues but struggling with structural dependencies.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.