1{2 "record_id": "2b0979784a826ff5181dbb43492b0239ca3062e8",3 "eligible": true,4 "short_ref": "Gillespie, Lyons & Hynes (2023)",5 "country": "Ireland",6 "city": "national (coastal properties within 5 km of the coast)",7 "property_type": "mixed (houses and apartments)",8 "price_type": "listing price (log); transaction-price subsample robustness",9 "n_obs": 100030,10 "sample_period": "2014-2019",11 "data_source": "daft.ie listings; Property Price Register for ~50,000 matched transactions; 10 m DEM viewsheds",12 "methods_compared": [13 "OLS hedonic with spatial fixed effects (6 levels of SFE)",14 "OLS with GIS-only view measures",15 "OLS with NLP-only sea-view dummy"16 ],17 "best_method": "OLS hedonic with Small Area + micro-market x year fixed effects",18 "metric": "R2",19 "best_value": 0.89,20 "hedonic_value": 0.89,21 "test_set": "none",22 "features_ai": "listing text (rule-based NLP sea-view detection)",23 "incremental_ai_gain": 0.0,24 "incremental_ai_metric": "R2 (in-sample)",25 "marginal_effects": "coefficients",26 "notes": "Hedonic study: rule-based NLP (NLTK pattern matching on ad text) flags sea views, GIS 3D viewsheds measure breadth/depth. Table 3 preferred specification R2 0.890, RMSE 0.222 (log price, in-sample). Table 4 separates GIS and NLP measures: R2 stays 0.890 and RMSE 0.222 in all six specifications, so the printed fit gain from the NLP feature is 0.000; its contribution is in coefficient identification (sea-view premium 8.2%, up to 15% for the top breadth quartile).",27 "confidence": "high"28}