Hybrid algorithms for recommending new items in personal TV

FutureTV-2011: Making Television Personal & Social 2011.

工业技术;计算机科学

Fabio Airoldi ; Paolo Cremonesi ; Roberto Turrin

Others  :  http://ceur-ws.org/Vol-720/Airoldi.pdf
PID  :  42418

来源: CEUR

【 摘 要 】

Recommending TV programs in the interactive TV domain is a difficult task since the catalog of available items is very dynamic, i.e., items are continuously added and removed. Despite recommender systems based on collaborative filtering typically outperform content-based systems in terms of recommendation quality, they suffer from the new item problem, i.e., they are not able to recommend items that have few or no ratings. On the contrary, content-based recommender systems are able to recommend both old and new items but the general quality of the recommendations in terms of relevance to the users is low. In this article we present two different approaches for building hybrid collaborative+content recommender systems, whose purpose is to produce relevant recommendations, while overcoming the new item issue. The approaches are tested on the implicit ratings collected from 15’000 IPTV users over a period of six months.