Mapping lived experience: A self-organizing map approach to comparing objective and subjective livability in Jakarta
Year: 2025
Type: article
Study design: Observational Study
Abstract: Assessing urban livability requires accounting for both the physical environment and residents’ perceptions. However, objective indicators (OI) derived from geospatial data and subjective indicators (SI) from surveys often yield conflicting insights, complicating evidence-based urban planning. This study addresses this challenge by comparing spatial patterns of OIs and SIs related to the built environment in Jakarta, Indonesia. We analyze ten objective indicators from GIS datasets alongside twelve subjective indicators from a survey of 1050 residents across three socio-spatially diverse districts. Employing a 100-m grid framework and Self-Organizing Maps, an unsupervised machine learning technique, we identify and contrast distinct livability clusters. Our analysis reveals a profound disconnect between the objective and subjective assessments, quantified by a remarkably low Normalized Mutual Information score of 0.091, indicating almost no statistical agreement between the two resulting classifications. This mismatch manifests spatially as large, coherent clusters based on physical data, which contrast to a fragmented mosaic of perceived livability. For example, in areas with uniform objective conditions, we find wide disparities in resident satisfaction, reflecting socio-economic inequalities not captured by physical metrics alone. These findings illustrate the limitations of relying exclusively on objective data and highlight the importance of incorporating residents lived experiences. We argue that integrating both types of indicators is essential for developing more equitable and responsive urban policies, particularly in rapidly urbanizing cities like Jakarta.
Source: Journal of Urban Management
Authors: Francisco Benita, Bayi Li, Rafael Martinez
Language: English
Subfield: Transportation
Field: Social Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $1,200
Award: G8726774674
OpenAlex ID: W4417447939
