Spatial Disparities in Short-term Rental Guest-Perceived Accommodation Quality: A Twelve-City Comparative Analysis Using Airbnb Review Data and Explainable Machine Learning
Abstract
Abstract Housing satisfaction has traditionally been measured through small-sample surveys with significant temporal lags, limiting its utility for spatial policy diagnostics. This study treats Airbnb guest reviews as a direct, systematically measurable expression of short-term rental guest-perceived accommodation quality (STR-GPAQ)—a bounded but meaningful signal of urban short-term rental service quality variation—examining spatial disparities across twelve cities spanning four continents with divergent short-term rental (STR) regulatory regimes. We develop an integrated explainable machine learning pipeline combining XGBoost binary classification, SHAP interpretability analysis, and the STR-GPAQ Inequality Index (SII)—a Gini-inspired metric specifically designed to measure inequality in the short-term rental guest-perceived quality domain, justified by axioms of distributional inequality measurement. While we retain the name SII for brevity, the index measures STR-GPAQ inequality, not general housing satisfaction. Our pipeline achieves a cross-validated accuracy of 0.867, AUC of 0.789 (spatial block CV AUC = 0.749 ± 0.020), and F1-score of 0.928 across 297,227 listings. The model exhibits near-zero negative-class recall (0.042), reflecting the inherent class imbalance in Airbnb review scores; SII therefore measures quality dispersion in the upper-mid to high range, not absolute deprivation. Amsterdam exhibits the lowest distributional inequality (SII = 0.031) alongside…
How strong is the evidence?
Evidence Hub reads this as a theoretical / analytical, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Understanding the factors influencing fall armyworm (Spodoptera frugiperda J.E. Smith) damage in African smallholder maize fields and quantifying its impact on yield. A case study in Eastern Zimbabwe
- Alarming situation of emerging H5 and H7 avian influenza and effective control strategies
- Livestock and food security: vulnerability to population growth and climate change
- Atmosphere–ocean oxygen and productivity dynamics during early animal radiations
- Characterization of the global distribution and diversified plasmid reservoirs of the colistin resistance gene mcr-9
- The global seroprevalence of Toxoplasma gondii in pigs: A systematic review and meta-analysis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.