移动新闻推荐技术及其应用研究综述  

A Survey of Mobile News Recommend Techniques and Applications

作　　者：孟祥武[1,2] 陈诚[1,2] 张玉洁[1,2] 

机构地区：[1]北京邮电大学智能通信软件与多媒体北京市重点实验室,北京100876 [2]北京邮电大学计算机学院,北京100876

出　　处：《计算机学报》2016年第4期685-703,共19页Chinese Journal of Computers

基　　金：国家自然科学基金(60872051);北京市教育委员会共建项目专项资助

摘　　要：随着移动设备的普及和新闻读者群体人数的不断增加,移动新闻推荐已经成为移动推荐领域的热点之一.如何根据移动设备和新闻特点进行移动新闻推荐,以提高推荐性能和用户满意度,成为移动新闻推荐系统的主要任务.文中概括分析了移动新闻推荐的研究现状,并指出其与传统新闻推荐、其他移动推荐之间的区别.从新闻表示方法,移动用户新闻偏好获取,上下文感知的移动新闻推荐技术,基于社会化网络的移动新闻推荐技术,移动新闻展示以及典型应用等六个关键方面,对移动新闻推荐领域的最新研究成果进行了详细的比较、分析和总结.文中还从重点、难点两个方面讨论分析了移动新闻推荐系统面临的挑战.并指出为了进一步发展移动新闻推荐系统,未来还需要在数据集获取,效用评估,结合移动社会化网络,安全问题,形式化描述等方面深入开展一些研究工作.With the popularity of mobile devices and the increasing amount of news readers,mobile news recommendation has become one of the hottest topics in the recommendation field.It is the main task of mobile news recommender systems,how to improve recommendation performance and user satisfaction according to the characters of mobile devices and news.This paper summarizes the research status of mobile news recommender and distinguishes it from traditional news recommender as well as mobile recommender for other purposes.Specially,from six key aspects,including news articles representation,news preference acquisition for mobile users,contextaware mobile news recommendation techniques,mobile news recommendation techniques based on social networks,news presentation on mobile devices and some typical applications,this paper provides a deep comparison,analysis and peroration of the latest research in the field of mobile news recommendation.Furthermore,we discuss and analyse the challenges in the field of mobile news recommender from the perspectives of key points and difficulties.Finally,we point out some future work to be done to promote the further development of mobile news recommender,particularly the acquisition of mobile news data sets,performance evaluation,the methods of incorporating with mobile social networks,security problem and formal description and so on.

关 键 词：个性化 上下文感知 移动社交网络 移动新闻推荐 社交媒体 数据挖掘 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]