Exportar Publicação

Correia, Ricardo Mendes, Guerreiro, Maria Rosália & Brandão, Filipe J.S. (2021). Spatial Analysis of Airbnb in Lisbon. A Network Kernel Density Estimation. Spatial Humanities 2021.

R. F. José et al.,  "Spatial Analysis of Airbnb in Lisbon. A Network Kernel Density Estimation", in Spatial Humanities 2021, Lisboa, 2021

@misc{josé2021_1766222024880,
	author = "Correia, Ricardo Mendes and Guerreiro, Maria Rosália and Brandão, Filipe J.S.",
	title = "Spatial Analysis of Airbnb in Lisbon. A Network Kernel Density Estimation",
	year = "2021",
	doi = "10.13140/RG.2.2.36757.03041",
	howpublished = "Ambos (impresso e digital)",
	url = "https://www.researchgate.net/publication/391600011_Spatial_Analysis_of_Airbnb_in_Lisbon_A_Network_Kernel_Density_Estimation"
}

TY  - CPAPER
TI  - Spatial Analysis of Airbnb in Lisbon. A Network Kernel Density Estimation
T2  - Spatial Humanities 2021
AU  - Correia, Ricardo Mendes
AU  - Guerreiro, Maria Rosália
AU  - Brandão, Filipe J.S.
PY  - 2021
DO  - 10.13140/RG.2.2.36757.03041
CY  - Lisboa
UR  - https://www.researchgate.net/publication/391600011_Spatial_Analysis_of_Airbnb_in_Lisbon_A_Network_Kernel_Density_Estimation
AB  - Airbnb can be considered an important urban phenomenon. It was a shared accommodation service that evolved to the rental of flats and buildings. It can be considered an Internet-based business model with disruptive potential for several businesses other than accommodation industry. 

In Lisbon, it is possible to confirm visualize through the use of georeferenced data  that Airbnb grew from 5652 leases available in March 2015 to 16717 leases in February 2019, an annual growth in offers of 86.32%.

Since it is an ongoing process within the cities, traditional statistical tools produced by national authorities have severe limitations when compared to spatial analysis tools.

Statistical methods in GIS, such as Kernel Density Estimation (KDE) can provide intensity measurement of urban phenomena like Airbnb, without the loss of underlying spatial information.

Being Airbnb an Internet-based business that shares the accommodation services coordinates we can use this spatial information with KDE as a convenient approach to determine Airbnb distribution with a large volume of data.

To get better results we are going to use KDE over network distances (NKDE) based on fact that buildings are not uniformly distributed but organized along a structure of streets. A network where most activity occurs.

This study proposes a methodology that can be useful for all stakeholders in the urban planning process.
We propose a way to determine the intensity of Airbnb events in Lisbon measuring NKDE intensity along streets and not on all urban area.

ER  -