A recommender geoportal for geospatial resource discovery and recommendation
(2019) In Journal of Spatial Science 64(1). p.49-71- Abstract
Geoportals have been widely implemented by national spatial data infrastructures (NSDI) to provide users with the ability to search for geospatial resources over the Internet. This paper proposes an approach that can improve the functionalities of the conventional geoportals by adding recommendation capabilities to the execution mechanisms of geoportals. The geoportals with recommendation capability are able to analyse users’ activities and recommend geospatial resources to users based on their desires and preferences. A hybrid recommendation mechanism based on the singular value decomposition (SVD) method is developed to provide required prediction and recommendation capabilities. Spatial attributes of geospatial resources along with... (More)
Geoportals have been widely implemented by national spatial data infrastructures (NSDI) to provide users with the ability to search for geospatial resources over the Internet. This paper proposes an approach that can improve the functionalities of the conventional geoportals by adding recommendation capabilities to the execution mechanisms of geoportals. The geoportals with recommendation capability are able to analyse users’ activities and recommend geospatial resources to users based on their desires and preferences. A hybrid recommendation mechanism based on the singular value decomposition (SVD) method is developed to provide required prediction and recommendation capabilities. Spatial attributes of geospatial resources along with users’ characteristics are utilised to improve the quality of the recommendations. To evaluate the feasibility of the proposed approach, a prototype system was developed and implemented. The results show that the recommender geoportal can relatively predict users’ desires and preferences and provide them with useful geospatial resources.
(Less)
- author
- Dareshiri, Shokouh ; Farnaghi, Mahdi LU and Sahelgozin, Mohammadreza
- publishing date
- 2019-01-02
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- geo-data, Geoportal, geospatial services, recommender system, singular value decomposition (SVD)
- in
- Journal of Spatial Science
- volume
- 64
- issue
- 1
- pages
- 23 pages
- publisher
- Taylor & Francis
- external identifiers
-
- scopus:85035781298
- ISSN
- 1449-8596
- DOI
- 10.1080/14498596.2017.1397559
- language
- English
- LU publication?
- no
- id
- 0c711cdc-5d53-4b57-9c45-bcf96650b973
- date added to LUP
- 2019-03-19 15:46:36
- date last changed
- 2022-04-25 22:03:34
@article{0c711cdc-5d53-4b57-9c45-bcf96650b973, abstract = {{<p>Geoportals have been widely implemented by national spatial data infrastructures (NSDI) to provide users with the ability to search for geospatial resources over the Internet. This paper proposes an approach that can improve the functionalities of the conventional geoportals by adding recommendation capabilities to the execution mechanisms of geoportals. The geoportals with recommendation capability are able to analyse users’ activities and recommend geospatial resources to users based on their desires and preferences. A hybrid recommendation mechanism based on the singular value decomposition (SVD) method is developed to provide required prediction and recommendation capabilities. Spatial attributes of geospatial resources along with users’ characteristics are utilised to improve the quality of the recommendations. To evaluate the feasibility of the proposed approach, a prototype system was developed and implemented. The results show that the recommender geoportal can relatively predict users’ desires and preferences and provide them with useful geospatial resources.</p>}}, author = {{Dareshiri, Shokouh and Farnaghi, Mahdi and Sahelgozin, Mohammadreza}}, issn = {{1449-8596}}, keywords = {{geo-data; Geoportal; geospatial services; recommender system; singular value decomposition (SVD)}}, language = {{eng}}, month = {{01}}, number = {{1}}, pages = {{49--71}}, publisher = {{Taylor & Francis}}, series = {{Journal of Spatial Science}}, title = {{A recommender geoportal for geospatial resource discovery and recommendation}}, url = {{http://dx.doi.org/10.1080/14498596.2017.1397559}}, doi = {{10.1080/14498596.2017.1397559}}, volume = {{64}}, year = {{2019}}, }