Personalized TV Recommendation: Fusing User Behavior and Preferences
Information Retrieval
2020-09-21 v1 Machine Learning
Machine Learning
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.
Cite
@article{arxiv.2009.08957,
title = {Personalized TV Recommendation: Fusing User Behavior and Preferences},
author = {Sheng-Chieh Lin and Ting-Wei Lin and Jing-Kai Lou and Ming-Feng Tsai and Chuan-Ju Wang},
journal= {arXiv preprint arXiv:2009.08957},
year = {2020}
}
Comments
8 pages