an adaptive strongsystemstrong for the personalized access to news.pdfVIP

1 An adaptive system for the personalized access to news Liliana Ardissono, Luca Console and Ilaria Torre ing strategies for adapting its behavior to each specific Dipartimento di Informatica, Universita` di Torino user (see [8, 10, 35]). Corso Svizzera 185 - 10149 Torino (Italy) Adaptive systems have been designed and applied E-mail: liliana,lconsole,ila.torre
@di.unito.it in different areas, such as intelligent tutoring [12, 15, 23, 28], access to information sources [40, 26, 16, 1, 18, 39, 49], electronic catalogues [42, 13, 38, 31, 20], Personalization is one of the keys for the success of web health-care assistance [29, 7, 17], information filtering services. In this paper we present SeAN (Server for Adap- and recommender systems [33, 4, 43, 6, 9, 5, 27, 21]. tive News), an adaptive system for the personalized access to These systems make use of different techniques as re- news servers on the WWW. The aims of the system are (i) gards both user modeling and adaptation. For exam- to select the sections (topics) and news in the server that are most relevant for each user, (ii) to customize the detail level ple, a model of a user can be generated after classifying of each news item to the user’s characteristics and (iii) to her into stereotypical pre-defined classes (as in [44]) select the advertisements that are most appropriate for each or using learning techniques after observing her be