Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Citado por Google
- Similares en SciELO
- Similares en Google
Compartir
Bitácora Urbano Territorial
versión impresa ISSN 0124-7913
Resumen
ABARCA-ALVAREZ, Francisco Javier; CAMPOS-SANCHEZ, Francisco Sergio y REINOSO-BELLIDO, Rafael. Signs of gentrification usin g Artificial Intelligence: identification through the Dwelling Census. Bitácora Urbano Territorial [online]. 2018, vol.28, n.2, pp.103-114. ISSN 0124-7913. https://doi.org/10.15446/bitacora.v28n2.70145.
Gentrification is not always detected by society, policy and planning in time to interpret its dynamics and implement interventions that mitigate its adverse effects. Its implications are so important in the social physiognomy of cities, that any tool that can predict or evidence any kind of sign of gentrification will be relevant. The research seeks to assess the feasibility of detecting areas linked to gentrification processes, incipient or settled, by using common sources of information in cities, such as the housing census. To this end, we propose the use of information extraction methodologies based on data mining techniques from Artificial Intelligence sciences. The methodology is evaluated experimentally in a complex and extensive territory, the Mediterranean coast of the Spanish peninsula. The results make it possible to identify an urban profile that includes all the neighbourhoods, to which the state of the art attributes gentrification, resulting in the proportion of rented dwellings that are essential for this purpose. It is concluded that the proposed methodology is useful to evidence territories with similar signs to urban environments with gentrification, allowing the early detection of similar processes in other areas.
Palabras clave : urban profile; artificial neural network; self-organizing map; forecast; gentrification.