Repozytorium publikacji - Politechnika Gdańska

Recommender systems aim to propose potentially interesting items to a user based on his preferences or previous interaction with the system. In the last decade, researcher found out that known recommendation techniques are not sufficient to predict user decisions. It has been noticed that user preferences strongly depend on the context in which he currently is. This raises new challenges for the researchers such as how to obtain contextual information, how to model context and use it to make predictions. In this paper we discuss the main idea of context-aware recommender systems and describe paradigms for incorporating context in recommendation process with some examples. We show how important and hard task is the choice of contextual parameters, present which of them are useful in different domains and describe a method for choosing relevant context variables. We also discuss different context-aware recommender systems that utilize ontologies in different ways in the recommendation process.

Autorzy

• dr inż. Aleksandra Karpus link otwiera się w nowej karcie