广播电视学外文文献 RecTime Real-Time recommender system for online broadcasting.pdfVIP

Information Sciences 409–410 (2017) 1–16 Contents lists available at ScienceDirect Information Sciences journal homepage: /locate/ins RecTime: Real-Time recommender system for online broadcasting a b b,∗ Yoojin Park , Jinoh Oh , Hwanjo Yu a LG Electronics Co., Seoul, South Korea b Pohang Universtiy of Science and Technology (POSTECH), Pohang, South Korea a r t i c l e i n f o a b s t r a c t Article history: Recommender systems for online broadcasting become important as the number of chan- Received 24 June 2016 nels has been increasing. In online broadcasting, to provide accurate recommendation, rec- Revised 17 April 2017 ommender systems should take time factors as well as users’ condition into account, but Accepted 22 April 2017 the conventional systems don’t. This paper proposes a real-time recommender system for Available online 28 April 2017 online broadcasting called RecTime which considers time factors and preferences simul- Keywords: taneously. Specifically, RecTime employs a 4-d tensor factorization, which considers two Recommendation more dimensions regarding the time factors, while typical collaboriative filtering methods TV show only consider two dimensions, users and