Tesis doctoral de Vanesa Aciar Silvana
The work developed in this thesis presents an in-depth study and provides innovative solutions in the field of recommender systems. The methods used by these systems to carry out recommendations, such as content-based filtering (cbf), collaborative filtering (cf) and knowledge-based filtering, require information from users to predict preferences for certain products. This may be demographic information (genre, age and address), evaluations given to certain products in the past or information about their interests. There are two ways of obtaining this information: users offer it explicitly or the system can retrieve the implicit information available in the purchase and search history. For example, the movie recommender system movielens (http://movielens.Umn.Edu/login) asks users to rate at least 15 movies on a scale of * to * * * * * (awful, … , Must be seen). The system generates recommendations based on these evaluations. When users are not registered into the site and it has not information about them, recommender systems make recommendations according to the site search history. Amazon.Com (http://www.Amazon.Com) make recommendations according to the site search history or recommend the best selling products. Nevertheless, these systems suffer from a certain lack of information [adomavicius, 2005]. This problem is generally solved with the acquisition of additional information; users are asked about their interests or that information is searched for in additional available sources. the solution proposed in this thesis is to look for that information in various sources, specifically those that contain implicit information about user preferences. These sources can be structured like databases with purchasing information or they can be unstructured sources like review pages where users write their experiences and opinions about a product they buy or possess. we have found three fundamental problems to achieve this objective: 1- the identification of sources
Datos académicos de la tesis doctoral «Information sources selection methodology for recommender systems based on intrinsics characteristics and trust measure«
- Título de la tesis: Information sources selection methodology for recommender systems based on intrinsics characteristics and trust measure
- Autor: Vanesa Aciar Silvana
- Universidad: Girona
- Fecha de lectura de la tesis: 18/06/2007
Dirección y tribunal
- Director de la tesis
- Josep Lluís De La Rosa I Esteva
- Tribunal
- Presidente del tribunal: john Debenham
- marcelo Royo vela (vocal)
- nuria Agell jané (vocal)
- christian Serarols tarrés (vocal)