Year: 2020
Type: preprint
Abstract: In this paper, we propose a two-stage ranking approach for recommending linear TV programs. The proposed approach first leverages user viewing patterns regarding time and TV channels to identify potential candidates for recommendation and then further leverages user preferences to rank these candidates given textual information about programs. To evaluate the method, we conduct empirical studies on a real-world TV dataset, the results of which demonstrate the superior performance of our model in terms of both recommendation accuracy and time efficiency.
Source: arXiv (Cornell University)
Authors: Lin, Sheng-Chieh, Lin, Ting-Wei, Lou, Jing-Kai, Tsai, Ming-Feng, Wang, Chuan-Ju
Institutions: Academia Sinica, National Chengchi University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3087393418