SCENE: a scalable two-stage personalized news recommendation system

Lei Li, Dingding Wang, Tao Li, Daniel Knox, Balaji Padmanabhan

Abstract: Recommending news articles has become a promising research direction as the Internet provides fast access to real-time information from multiple sources around the world. Traditional news recommendation systems strive to adapt their services to individual users by virtue of both user and news content information. However, the latent relationships among different news items, and the special properties of new articles, such as short shelf lives and value of immediacy, render the previous approaches inefficient. In this paper, we propose a scalable two-stage personalized news recommendation approach with a two-level representation, which considers the exclusive characteristics (e.g., news content, access patterns, named entities, popularity and recency) of news items when performing recommendation. Also, a principled framework for news selection based on the intrinsic property of user interest is presented, with a good balance between the novelty and diversity of the recommended result. Extensive empirical experiments on a collection of news articles obtained from various news websites demonstrate the efficacy and efficiency of our approach.