Modeling and broadening temporal user interest in personalized news recommendation

作者：

Highlights：

• An experimental study on user interest evolution in real-world recommender systems.

• Integrating the long-term and short-term reading preferences of users.

• Selecting news from the user-item affinity graph using absorbing random walk model.

• Extensive empirical experiments on news data obtained from popular news websites.

摘要

•An experimental study on user interest evolution in real-world recommender systems.•Integrating the long-term and short-term reading preferences of users.•Selecting news from the user-item affinity graph using absorbing random walk model.•Extensive empirical experiments on news data obtained from popular news websites.

论文关键词：News recommendation,Personalization,Profile integration,Time sensitive weighting,Long-term profile,Short-term profile,Absorbing random walk,Recommendation diversity

论文评审过程：Available online 26 November 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.11.020