Knowledge intensive session modeling and mixed initiative recommendation are introduced in the CBR framework. The advantages of this approach, with respect to traditional web logs plus Data Mining, are shown. On-line, dynamic identification of in-context past similar sessions is exploited for building personalized recommendations. Session components, which are hierarchically structured, are selectively exploited in the system range of recommendation functions. The application of these ideas to an interactive, case-based travel recommender system, that guides European travelers for their decision making processes, is described
Case Based Session Modeling and Personalization in a Travel Advisory System
Arslan, Bora;Ricci, Francesco
2002-01-01
Abstract
Knowledge intensive session modeling and mixed initiative recommendation are introduced in the CBR framework. The advantages of this approach, with respect to traditional web logs plus Data Mining, are shown. On-line, dynamic identification of in-context past similar sessions is exploited for building personalized recommendations. Session components, which are hierarchically structured, are selectively exploited in the system range of recommendation functions. The application of these ideas to an interactive, case-based travel recommender system, that guides European travelers for their decision making processes, is describedFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
