Towards an integration of space and accessibility in Web personalization Mohamed Ramzi Haddad 1 , Hajer Baazaoui 1 , Marie Aude Aufaure 2,3 , Christophe Claramunt 4 , Yves Lechevallier 2 , and Henda Ben Ghezala 1 1 Riadi-Gdl Laboratory, haddad.medramzi@gmail.com, hajer.baazaouizghal@riadi.rnu.tn, henda.benghezala@riadi.rnu.tn Riadi-Gdl Laboratory, ENSI Tunis, Campus la Manouba, La Manouba, 2010, Tunisia 2 INRIA-Rocquencourt, Yves.Lechevallier@inria.fr INRIA-Rocquencourt, Domaine de Voluceau. 78 153 Le Chesnay Cedex, France 3 MAS Loboratory, marie-aude.aufaure@inria.fr Ecole Centrale Paris, MAS Laboratory. Chaire SAP BusinessObjects Grande Voie des Vignes 92 295 Chatenay-Malabry, France 4 Naval Academy Research Institute, christophe.claramunt@ecole-navale.fr Naval Academy Research Institute, Lanvoc-Poulmic, BP 600, Brest naval, France Abstract. Web personalization can be seen as an interdisciplinary domain that facilitates interaction between web content and user needs. One of the peculiar- ities of Web information is that a significant part of the data is georeferenced although this is not completely taken into account by current search and person- alization engines. This paper introduces a spatial personalization approach based on a user modeling technique and a measure of spatial accessibility. We develop a personalized accessibility measure whose objective is to predict and evaluate location relevancy, accessibility and associations at the user level. This measure favors delivery of location-based and personalized recommendations. 1 Introduction The main objective of personalization systems is to collect users’ preferences in order to better tailor services and information to their needs. The principal task of a per- sonalization process is to model the user and/or her/his context to analyze data from an individual point of view, predict content relevancy and facilitate data exploration, visualization and filtering. When manipulating spatial data, an effective personaliza- tion approach should take into account not only spatial data properties (i.e., location attributes and characteristics), but also existing spatial constraints and/or associations derived from the user’s spatial context. Personalization is closely related to a set of concepts to be taken into consideration such as user preferences, constraints and needs. A user model can be considered as a necessary condition to make a bridge between the user’s point of view, and relevancy