直播电视推荐系统的评分预测算法研究

doi:10.3969/j.issn.0372-2112.2020.09.010

电子学报 ›› 2020, Vol. 48 ›› Issue (9): 1735-1740.DOI: 10.3969/j.issn.0372-2112.2020.09.010

直播电视推荐系统的评分预测算法研究

郭景峰^1,2,3, 朱晓松^1,2,3, 李爽^4,5

1. 燕山大学信息科学与工程学院, 河北秦皇岛 066004;
2. 河北省计算机虚拟技术与系统集成重点实验室, 河北秦皇岛 066004;
3. 河北省文化旅游大数据技术创新中心, 河北承德 067000;
4. 天津大学建筑学院, 天津 300072;
5. 河北环境工程学院生态系, 河北秦皇岛 066102

收稿日期:2019-11-21 修回日期:2020-05-09 出版日期:2020-09-25
- 通讯作者:
- 朱晓松
- 作者简介:
- 郭景峰 男,1962年2月出生于黑龙江哈尔滨.现为燕山大学信息科学与工程学院教授、博士生导师.在国内外发表学术论文130余篇.E-mail:jfguo@ysu.edu.cn
  李爽女,1982年7月出生于河北唐山.现为河北环境工程学院副教授,天津大学建筑学院博士生,主要研究方向为数字景观、机器学习.E-mail:89732212@qq.com
- 基金资助:
- 国家自然科学基金 (No.61472340）; 河北省重点研发计划项目 (No.20310301D）

Research on Rating Prediction Algorithm of Live TV Recommender Systems

GUO Jing-feng^1,2,3, ZHU Xiao-song^1,2,3, LI Shuang^4,5

1. College of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China;
2. The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Qinhuangdao, Hebei 066004, China;
3. The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province, Chengde, Hebei 067000, China;
4. School of Architecture, Tianjin University, Tianjin 300072, China;
5. Faculty of Ecology, Environmental Management College of China, Qinhuangdao, Hebei 066102, China

Received:2019-11-21 Revised:2020-05-09 Online:2020-09-25 Published:2020-09-25
- Corresponding author:
- ZHU Xiao-song
- Supported by:
- National Natural Science Foundation of China (No.61472340); Key Reseach and Development Project of Hebei Province (No.20310301D)

摘要/Abstract

摘要： 伴随电视频道的不断增加，推荐系统在直播电视领域应用成为研究热点.然而，直播电视独特的播放和收视方式使得传统的VOD（Video On Demand）推荐系统无法直接应用，已有的推荐频道的方法不关注正在播出的节目状态从而影响了推荐准确率，而推荐节目的方法难以应对节目冷启动.为此，本文提出了一种融合频道推荐和节目推荐的评分预测算法OFAP（Over the First by Adding Preference）.首先，利用聚类方法对每个用户实现差异性的收视时段划分，构建他们的频道-时段偏好矩阵和预推荐评分权重矩阵；其次，提出一个评分替代策略使得已有的推荐节目的算法能够应对节目冷启动，从而实现预推荐；最后，通过融合用户偏好、预推荐评分权重与预推荐结果，构建评分预测函数，将预推荐算法的评分预测结果作为评分预测函数的训练样本.实验表明，采用Precision@N和Recall@N作为评价标准，本文所提方法OFAP明显优于对比算法.

Abstract: With the increase of TV channels, the application of recommender systems in the field of live TV has become a research hotspot. However, a traditional VOD (Video on Demand) recommender system is unable to be directly applied in live TV because of its special way of broadcasting and watching, and the existing methods of recommending channels do not pay attention to status of TV shows being broadcasted, which affects recommendation accuracy, and the methods of recommending programs are difficult to handle cold start of TV shows. Therefore, this paper proposes a rating prediction algorithm by fusing TV channel recommendation method and TV program recommendation method OFAP (Over the First by Adding Preference). Firstly, we construct different channel-time preference matrix and rating weight matrix of pre-recommendation for each user by clustering their viewing logs. Secondly, we propose a rating strategy to alleviate the cold-start problem of TV programs for existing program recommendation algorithms, and we adopt one of them to perform pre-recommendation. Finally, we combine user's preference, rating weight and rating of pre-recommendation to construct a prediction function, which is trained with the results of pre-recommendation. Experiments on industrial datasets show that the proposed model OFAP significantly outperforms baseline algorithms when Precision@N and Recall@N are adopted as criterias.

Key words: live TV, recommender system, cold start, time-based, pre-recommendation, collaborative filtering, TV channel

中图分类号:

TP302
TP391

郭景峰, 朱晓松, 李爽. 直播电视推荐系统的评分预测算法研究[J]. 电子学报, 2020, 48(9): 1735-1740.

GUO Jing-feng, ZHU Xiao-song, LI Shuang . Research on Rating Prediction Algorithm of Live TV Recommender Systems[J]. Acta Electronica Sinica, 2020, 48(9): 1735-1740.

参考文献

[1] Cremonesi P,Modica P,Pagano R,et al.Personalized and context-aware TV program recommendations based on implicit feedback[A].Proceedings of 16th International Conference on Electronic Commerce and Web Technologies[C].Valencia,Spain:Springer,2015.57-68.
[2] Wang Z,He L.User identification for enhancing IP-TV recommendation[J].Knowledge-Based Systems,2016,98:68-75.
[3] Turrin R,Condorelli A,Cremonesi P,et al.Time-based TV programs prediction[A].First Workshop on Recommender Systems for Television and Online Video at ACM RecSys'14[C].Silicon Valley,California,USA:ACM,2014.
[4] Oh J,Kim S,Kim J,et al.When to recommend:A new issue on TV show recommendation[J].Information Sciences,2014,280:261-274.
[5] Jin Y,Junhua G,Suqi Z,et al.Spark-based distributed multi-features hybrid IPTV viewing implicit feedback scoring model[J].Procedia Computer Science,2017,111:441-447.
[6] Cho K J,Lee Y C,Han K,et al.No,that's not my feedback:TV show recommendation using watchable interval[A].Proceedings of IEEE 35th International Conference on Data Engineering[C].Macau,China:IEEE,2019.316-327.
[7] Park Y,Oh J,Yu H.Rectime:Real-time recommender system for online broadcasting[J].Information Sciences,2017,409:1-16.
[8] Chang N,Irvan M,Terano T.A TV program recommender framework[J].Procedia Computer Science,2013,22:561-570.
[9] Bambini R,Cremonesi P,Turrin R.Recommender Systems Handbook[M].Berlin:Springer,2011.
[10] Karatzoglou A,Amatriain X,Baltrunas L,et al.Multiverse recommendation:n-dimensional tensor factorization for context-aware collaborative filtering[A].Proceedings of the 4th ACM Conference on Recommender Systems[C].Barcelona,Spain:ACM,2010.79-86.
[11] Yu C,Ding H,Cao H,et al.Follow me:personalized IPTV channel switching guide[A].Proceedings of the 8th ACM on Multimedia Systems Conference[C].Taipei,Taiwan,China:ACM,2017.147-157.
[12] Hu Y,Koren Y,Volinsky C.Collaborative filtering for implicit feedback datasets[A].Proceedings of the 8th IEEE International Conference on Data Mining[C].Pisa,Italy:IEEE,2008.263-272.
[13] Xin Y,Steck H.Multi-value probabilistic matrix factorization for IP-TV recommendations[A].Proceedings of the 5th ACM Conference on Recommender Systems[C].Chicago,Illinois,USA:ACM,2011.221-228.
[14] Zhang Z K,Liu C,Zhang Y C,et al.Solving the cold-start problem in recommender systems with social tags[J].Europhysics Letters,2010,92(2):28002-28007.
[15] Zhang R,Deng Y,Shi L.User research and design for live TV UX in China[A].Proceedings of Adjunct Publication of the 2017 ACM International Conference on Interactive Experiences for TV and Online Video[C].New York,NY,USA:ACM,2017.9-14.

直播电视推荐系统的评分预测算法研究

Research on Rating Prediction Algorithm of Live TV Recommender Systems

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	曹阳, 高旻, 余俊良, 范琪琳, 荣文戈, 文俊浩. 基于双图混合随机游走的社会化推荐模型[J]. 电子学报, 2023, 51(2): 286-296.
[2]	张帅, 高旻, 文俊浩, 熊庆宇, 唐旭. 基于自监督学习的去流行度偏差推荐方法[J]. 电子学报, 2022, 50(10): 2361-2371.
[3]	郑孝遥, 罗永龙, 汪祥舜, 孙丽萍, 陈付龙, 胡桂银, 汪小寒. 基于位置服务的分布式差分隐私推荐方法研究[J]. 电子学报, 2021, 49(1): 99-110.
[4]	黄名选, 蒋曹清. 基于项权值排序挖掘的跨语言查询扩展[J]. 电子学报, 2020, 48(3): 568-576.
[5]	杨洁, 朱咸军, 周献中, 柳毅. 基于混杂社会网络的个性化Web服务推荐方法[J]. 电子学报, 2020, 48(2): 341-349.
[6]	任开旭, 王玉龙, 刘同存, 李炜. 融合多维语义表示的概率矩阵分解模型[J]. 电子学报, 2019, 47(9): 1848-1854.
[7]	刘露, 胡封晔, 牛亮, 彭涛. 异质网络中基于节点影响力的相似度度量方法[J]. 电子学报, 2019, 47(9): 1929-1936.
[8]	李林峰, 刘真, 魏港明, 任爽, 葛梦凡. 基于共享知识模型的跨领域推荐算法[J]. 电子学报, 2018, 46(8): 1947-1953.
[9]	肖云鹏, 孙华超, 戴天骥, 李茜, 李暾. 一种基于云模型的社交网络推荐系统评分预测方法[J]. 电子学报, 2018, 46(7): 1762-1767.
[10]	肖云鹏, 刘晏驰, 刘红, 刘媛妮. 一种基于动态角色标识和张量分解的推荐模型[J]. 电子学报, 2018, 46(3): 569-574.
[11]	鲜征征, 李启良, 黄晓宇, 陆寄远, 李磊. 融合显/隐式信任协同过滤算法的差分隐私保护[J]. 电子学报, 2018, 46(12): 3050-3059.
[12]	黄名选, 蒋曹清. 基于完全加权正负关联模式挖掘的越-英跨语言查询译后扩展[J]. 电子学报, 2018, 46(12): 3029-3036.
[13]	俞东进, 陈聪, 吴建华, 陈耀旺. 基于隐式反馈数据的个性化游戏推荐[J]. 电子学报, 2018, 46(11): 2626-2632.
[14]	范利云, 左万利, 王英, 王鑫. 一种基于差分隐私和时序的推荐系统模型研究[J]. 电子学报, 2017, 45(9): 2057-2064.
[15]	俞春花, 刘学军, 李斌, 章玮. 基于上下文相似度和社会网络的移动服务推荐方法[J]. 电子学报, 2017, 45(6): 1530-1536.