Mining IPTV user behaviors with a coupled LDA model

In this paper, we analyze user behaviors in Internet Protocol television (IPTV). We propose a novel coupled LDA model, which considers topic of TV programs viewed as well as the timestamps of the viewing behaviors, in order to capture the inherent viewing patterns of the users along the topic as well as the time dimensions. Based on the coupled LDA model, we further summarize the behavior patterns of IPTV users. We compare our model with other models on the real data collected from an operational nation-wide IPTV system and show that the proposed coupled LDA model is able to capture interesting viewing patterns.