W. Nejdl and P. De Bra (Eds.): AH 2004, LNCS 3137, pp. 65–74, 2004. © Springer-Verlag Berlin Heidelberg 2004 Adaptive User Modeling for Personalization of Web Contents * Alberto Díaz 1 and Pablo Gervás 2 1 CES Felipe II – Universidad Complutense de Madrid c/ Capitán 39, 28300 Aranjuez, Madrid adiaz@cesfelipesegundo.com 2 Departamento de Sistemas Informáticos y Programación Facultad de Informática – Universidad Complutense de Madrid c/ Juan del Rosal, 8, Madrid 28040 pgervas@sip.ucm.es Abstract. This paper presents a system for personalization of web contents based on a user model that stores long term and short term interests. Long term interests are modeled through the selection of specific and general categories, and keywords for which the user needs information. However, user needs change over time as a result of his interaction with received information. For this reason, the user model must be capable of adapting to those shifts in inter- est. In our case, this adaptation of the user model is performed by a short term model obtained from user provided feedback. The evaluation performed with 100 users during 15 days has determined that the combined use of long and short term models performs best when specific and general categories and key- words are used together for the long term model. 1 Introduction Web content appears in many forms over different domains of application, but in most cases the form of presentation is the same for all users. The contents are static in the sense that they are not adapted to each user. Content personalization is a technique that tries to avoid information overload through the adaptation of web contents to each type of user. A personalization system is based on 3 main functionalities: content selection, user model adaptation, and content generation. For these functionalities to be carried out in a personalized manner, they must be based on information related to the user that must be reflected in his user profile or user model [8]. Content selection refers to the choice of the particular subset of all available docu- ments that will be more relevant for a given user, as represented in his user profile or model. In order to effect this choice one must have a representation of the documents, a representation of the user profile, and a similarity function that computes the level of adequacy of one to the other. * This research has been partially funded by the Spanish Ministerio de Ciencia y Tecnología (TIC2002-01961).