# RECORD 2b0979784a826ff5181dbb43492b0239ca3062e8 # TITLE: The Value of a Sea View: Hedonic Estimates Using 3D Simulation and Natural Language Processing # YEAR: 2023.0 VENUE: Land Economics DOI: 10.3368/le.100.2.071522-0056r # AUTHORS: Tom Gillespie; Ronan C. Lyons; Stephen Hynes # PAGES: 42 CANDIDATE TABLE PAGES (1-based): [36, 37, 38] # ABSTRACT: This article develops a new measure of sea view breadth and depth, based on a combination of GIS 3D simulation and natural language processing (NLP) techniques. NLP identifies properties that have a sea view, while GIS measures its extent. We estimate the value of a sea view using a hedonic housing price model and a sample of over 100,000 sales listings in Ireland, 2014–2019. We find that a sea view can add significant value to a property, all else being equal, with an average premium of 8.1% rising to 15% for a wide breadth of sea view. ===== PAGE 1 (score 4, numeric-paren 0, table-words 0, var-words 4) ===== 1 The Value of a Sea View: Hedonic Estimates Using 3D Simulation and Natural Language Processing Dr. Tom Gillespie Prof. Ronan C. Lyons† Prof. Stephen Hynes‡ Abstract This paper develops a novel measure of sea-view breadth and depth, based on a combination of GIS 3D simulation and Natural Language Processing (NLP) techniques. NLP identifies properties that have a sea view, while GIS measures its extent. It then estimates the value of a sea view using a hedonic housing price model and a sample of over 100,000 sales listings in Ireland, 2014-2019. We find that a sea view can add significant value to a property, all else being equal, with an average premium of 8.1% rising to 15% for a wide breadth of sea view.  Socio-Economic Marine Research Unit, Whitaker Institute, University of Galway. Thomas.gillespie@universityofgalway.ie † Department of Economics, Trinity College Dublin, and Spatial Economics Research Centre, LSE. Ronan.lyons@tcd.ie ‡ Socio-Economic Marine Research Unit, Whitaker Institute, University of Galway. Stephen.hynes@universityofgalway.ie doi:10.3368/le.100.2.071522-0056R by guest on October 20, 2026. Copyright 2023 Downloaded from ===== PAGE 36 (score 22, numeric-paren 0, table-words 4, var-words 8) ===== 36 Table 3: Baseline results Treatment of SE Robust Standard errors & Clustered at level of SFE Level of spatial FE Local Market Micro market Electoral District Small Area ED*Ye ar SA + MM*Year Dependent Variable: natural log of the listed sale price Coastal Variables Distance To Coastline (log) -0.038 -0.046 -0.040 -0.061 -0.038 -0.061 0.00 0.00 0.00 0.00 0.00 0.00 Distance To Transitional (log) -0.012 -0.012 -0.018 -0.014 -0.018 -0.014 0.34 0.10 0.00 0.01 0.01 0.01 Sea View Variables Seaview breadth 0.010 0.011 0.011 0.011 0.011 0.011 0.08 0.01 0.00 0.00 0.00 0.00 Seaview depth 0.023 0.020 0.018 0.013 0.017 0.013 0.04 0.00 0.00 0.00 0.00 0.00 Controls YES YES YES YES YES YES Observations 100,030 100,030 100,030 100,030 100,030 100,030 R-squared 0.800 0.841 0.854 0.882 0.868 0.890 RMSE 0.289 0.258 0.248 0.228 0.240 0.222 Number of absorbed SFE 50 261 832 5,571 4,509 5,571 Notes: Robust p-values, clustered at the level of spatial fixed effect, are reported below coefficients. Columns show different levels of spatial fixed effects denoted at header, while controls include location, dwelling and time listed on the market, as discussed in the text. by guest on October 20, 2026. Copyright 2023 Downloaded from ===== PAGE 37 (score 20, numeric-paren 0, table-words 4, var-words 7) ===== 37 Table 4: Separating GIS and NLP measures of views Treatment of SE Robust Standard errors & Clustered at level of SFE Level of spatial FE Small Area & Micro-Market*Year Specification Number Baseline 1 2 3 4 5 Dependent Variable: natural log of the listed sale price Coastal Variables Distance To Coastline (log) -0.061 -0.062 -0.062 -0.062 -0.061 -0.060 0.00 0.00 0.00 0.00 0.00 0.00 Distance To Transitional (log) -0.014 -0.015 -0.014 -0.015 -0.012 -0.013 0.01 0.01 0.01 0.01 0.02 0.01 Sea View Variables Seaview breadth 0.011 0.00 Seaview depth 0.013 0.00 Sea View Variables (GIS only) Seaview breadth 0.003 0.008 0.14 0.00 Seaview depth 0.013 0.015 0.00 0.00 Sea Views NLP 0.082 0.00 Sea Views NLP (GIS=0) 0.079 0.00 Controls YES YES YES YES YES YES Observations 100,030 100,030 100,030 100,030 100,030 100,030 R-squared 0.890 0.890 0.890 0.890 0.890 0.890 RMSE 0.222 0.222 0.222 0.222 0.222 0.222 Number of absorbed SFE 5,571 5,571 5,571 5,571 5,571 5,571 Notes: Robust p-values, clustered at the level of spatial fixed effect, are reported below coefficients. Columns show different robustness specifications numbered in the headers, while controls include location, dwelling and time listed on the market, as discussed in the text. by guest on October 20, 2026. Copyright 2023 Downloaded from ===== PAGE 38 (score 21, numeric-paren 0, table-words 4, var-words 9) ===== 38 Table 1: Controlling for the total viewshed of a property Treatment of SE Robust Standard errors & Clustered at level of SFE Level of spatial FE Small Area & Micro-Market*Year Specification Baseline Adding Land Viewshed Adding Slope Adding Land Viewshed and Slope Dependent Variable: natural log of.. Listed sale price Coastal Variables Distance To Coastline (log) -0.060 -0.061 -0.060 -0.061 0.00 0.00 0.00 0.00 Distance To Transitional (log) -0.015 -0.016 -0.015 -0.016 0.01 0.00 0.01 0.00 Sea View Variables Seaview breadth 0.011 0.011 0.011 0.011 0.00 0.00 0.00 0.00 Seaview depth 0.013 0.012 0.013 0.012 0.00 0.00 0.00 0.00 Land view and Slope Controls Log of Land Area Viewshed 0.005 0.005 0.00 0.00 Log of % Rise of Slope 0.000 0.001 0.97 0.83 Controls YES YES YES YES Observations 99,447 99,447 99,447 99,447 R-squared 0.890 0.890 0.890 0.890 RMSE 0.221 0.221 0.221 0.221 Number of absorbed SFE 5,566 5,566 5,566 5,566 Notes: Robust p-values, clustered at the level of spatial fixed effect, are reported below coefficients. Columns show different levels of spatial fixed effects denoted at header, while controls include location, dwelling and time listed on the market, as discussed in the text. by guest on October 20, 2026. Copyright 2023 Downloaded from ===== PAGE 39 (score 7, numeric-paren 0, table-words 2, var-words 3) ===== 39 Figure Titles Figure 1. Distribution of visible points as a function of distance to coastline Note: The above figure shows summary statistics of the number of (inner) points visible for properties with at least one inner point visible in their viewshed, by distance to the coastline, with sample sizes for each distance bin reported in the horizontal axis. Figure 2. Graph of sea view coefficients by level of SFE – Illustrating the results from Table 3. Notes: The above figure displays point estimates and confidence intervals for the results in table 3. by guest on October 20, 2026. Copyright 2023 Downloaded from