Skip to content Skip to navigation

Najava predavanja profesora Francesca Riccia iz Free University of Bozen-Bolzano: "Context-Aware Recommender Systems"

U sklopu predmeta Inteligentni sustavi za ponedjeljak, 13. lipnja 2011. u 11:00 sati u dvorani 10, najavljujemo predavanje vrlo uglednog znanstvenika na tom području, profesora Francesca Riccia. Predavanje posebno preporučujemo studentima na višim godinama studija, studentima doktorskog studija, koji su zainteresirani za znanstvena istraživanja i napredne aplikacije umjetne inteligencije i mobilnih tehnologija u elektroničkom podlovanju i turizmu. 

Profesor Francesco Ricci jedan je od vodećih znanstvenika na području sustava za preporuku, s naglaskom na primjenu u turizmu. Područja od interesa u znanosti su mu: sustavi za preporuku, modeliranje korisnika, adaptivni i sustavi za konverzaciju, zaključivanje temeljeno na slučajevima (Case-Based Reasoning), strojno učenje, zaključivanje temeljeno na ograničenjima, elektroničko poslovanje i turizam.  Predaje slijedeće kolegije: Information Search and Retrieval, Internet and Mobile Services, Internet Technologies, Research Methods. Sudjelovao je u razvoju i istraživanju i razvoju sustava za preporuke: NutKing, DieToRecs, and MobyRek. Urednik je knjige: Recommender Systems Handbook. Bio je podpredsjednik desetak međunarodnih konferencija, član programskog odbora oko pedesetak konferencija. Dodatne informacije o profesoru Ricciu možete dobiti na stranici: http://www.inf.unibz.it/~ricci/.

Sažetak predavanja:

Context-Aware Recommender Systems

Recommender Systems are software tools and techniques providing suggestions for items to be of use to a user. Context is providing information that can influence the perception of the usefulness of an item for a user. For this reason Recommender Systems must take into account this information to deliver more useful (perceived) recommendations. There are several examples motivating the importance of context for recommender systems. For instance, to suggest a meaningful travel to a user a RS must know if the travel is scheduled in summer or winter, and if the user is traveling alone or with kids. Moreover, only taking into account the context of an item evaluation, the user can assign a proper value to that item. For instance while one can judge a Ferrari a 5 star car; this does not mean that it is a proper recommendation if the user is looking for a new car to buy. Context modeling and context-dependent reasoning is a complex subject and still there are major technical and practical difficulties to solve: obtain sufficient and reliable data describing the user preferences in context; selecting the right context information, i.e., relevant in a particular personalization task; understanding the impact of the contextual dimensions on the personalization process; embedding the contextual dimensions in a recommendation computational model. These topics will be illustrated in the talk, making references to many examples taken by recommender systems that we have developed.