• Corpus ID: 17893506

Recommender-based enhancement of discovery in Geoportals

  title={Recommender-based enhancement of discovery in Geoportals},
  author={Bernhard Vockner and Mariana Belgiu and Manfred Mittlb{\"o}ck},
  journal={Int. J. Spatial Data Infrastructures Res.},
In many cases web search engines like Google are still used for discovery of geographic base information. This can be explained by the fact that existing approaches for Geo-information retrieval still face significant challenges. Discovery in currently available Geoportals is usually restricted to text-based search based on keywords, title and abstract as well as applying spatial and temporal filters. Furthermore, user context as well as search results of other users are not incorporated. In… 

Figures from this paper

From Geoportals to Geographic Knowledge Portals

We present the application of Latent Semantic Analysis (LSA) in combination with recommender systems, in order to enhance discovery in geoportals. As a basis for discovery, metadata of spatial data

A recommender geoportal for geospatial resource discovery and recommendation

The results show that the recommender geoportal can relatively predict users’ desires and preferences and provide them with useful geospatial resources.



Item-based collaborative filtering recommendation algorithms

This paper analyzes item-based collaborative ltering techniques and suggests that item- based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.

Resource Discovery in a European Spatial Data Infrastructure

It is concluded that it will be impractical to rely only on one common ontology for resource discovery and that the approach of using human-created ontologies in combination with automatic concept space generation and associative retrieval is a powerful means to the discovery of geospatial resources.

Fab: content-based, collaborative recommendation

It is explained how a hybrid system can incorporate the advantages of both methods while inheriting the disadvantages of neither, and how the particular design of the Fab architecture brings two additional benefits.

A Framework for Collaborative, Content-Based and Demographic Filtering

  • M. Pazzani
  • Computer Science
    Artificial Intelligence Review
  • 2004
The types of information available to determine whether to recommend a particular page to a particular user are described and how each type of information may be used individually and an approach to combining recommendations from multiple sources are discussed.


A conceptual framework flexible enough to integrate existing domain knowledge bases and utilizes lightweight ontologies for explicit specification of domain conceptualization and maps domain concepts against related concepts defined in other formalized concepts schemas is described.

Slope One Predictors for Online Rating-Based Collaborative Filtering

Three related slope one schemes with predictors of the form f(x) = x + b are proposed with results competitive with slower memory-based schemes over the standard benchmark EachMovie and Movielens data sets while better fulfilling the desiderata of CF applications.

Recommender systems

This special section includes descriptions of five recommender systems, which provide recommendations as inputs, which the system then aggregates and directs to appropriate recipients, and which combine evaluations with content analysis.

Towards Privacy-Aware Location-Based Recommender Systems

An overview of the working principles of current location-based recommender systems is given, analysing them from the user privacy perspective and calling for a new approach to location- based recommendation based on homomorphic encryption in order to enhance users’ privacy.