融合评论分析和隐语义模型的视频推荐算法

doi:10.11772/j.issn.1001-9081.2015.11.3247

计算机应用 ›› 2015, Vol. 35 ›› Issue (11): 3247-3251.DOI: 10.11772/j.issn.1001-9081.2015.11.3247

融合评论分析和隐语义模型的视频推荐算法

尹路通¹, 于炯^1,2, 鲁亮², 英昌甜², 郭刚¹

1. 新疆大学软件学院, 乌鲁木齐 830008;
2. 新疆大学信息科学与工程学院, 乌鲁木齐 830046

收稿日期:2015-05-23 修回日期:2015-07-10 发布日期:2015-11-13
通讯作者: 于炯(1964-),男,北京人,教授,博士生导师,博士,CCF会员,主要研究方向:网络安全、网格与分布式计算.
作者简介:尹路通(1992-),男,河南驻马店人,硕士研究生,主要研究方向:大数据与数据挖掘、推荐系统; 鲁亮(1989-),男,新疆乌鲁木齐人,博士研究生,CCF会员,主要研究方向:云计算、分布式计算; 英昌甜(1989-),女,新疆乌鲁木齐人,博士研究生,CCF会员,主要研究方向:云计算与存储节能; 郭刚(1990-),男,山东枣庄人,硕士研究生,主要研究方向:大数据存储、数据迁移.
基金资助:
国家自然科学基金资助项目(61462079,61363083,61262088).

Video recommendation algorithm fusing comment analysis and latent factor model

YIN Lutong¹, YU Jiong^1,2, LU Liang², YING Changtian², GUO Gang¹

1. School of Software, Xinjiang University, Urumqi Xinjiang 830008, China;
2. School of Information Science and Engineering, Xinjiang University, Urumqi Xinjiang 830046, China

Received:2015-05-23 Revised:2015-07-10 Published:2015-11-13

摘要/Abstract

摘要： 针对网络视频元数据信息缺失严重和多媒体数据本身特征难以提取等问题,提出了融合评论分析和隐语义模型的网络视频推荐算法.从视频评论入手,通过分析用户对不同视频的评论内容以判断其情感倾向并加以量化,继而构建用户对项目的虚拟评分矩阵,弥补了显式评分数据稀疏性问题.考虑到网络视频的多元性和高维度特性,为了深度挖掘用户对网络视频的潜在兴趣,针对虚拟评分矩阵采用隐语义模型(LFM)对网络视频分类,在传统的用户—项目二元推荐系统基础之上添加虚拟类目信息以进一步发掘用户—类目—项目关联关系.实验在多重标准下进行,对YouTube评论集的实验表明,所提推荐方法获得了较高的推荐精度.

关键词: 推荐系统, 网络视频, 评论分析, 隐语义模型, 情感词

Abstract: Video recommender is still confronted with many challenges such as lack of meta-data of online videos, and also it's difficult to abstract features on multi-media data directly. Therefore an Video Recommendation algorithm Fusing Comment analysis and Latent factor model (VRFCL) was proposed. Starting with video comments, it firstly analyzed the sentiment orientation of user comments on multiple videos, and resulted with some numeric values representing user's attitude towards corresponding video. Then it constructed a virtual rating matrix based on numeric values calculated before, which made up for data sparsity to some extent. Taking diversity and high dimensionality features of online video into consideration, in order to dig deeper about user's latent interest into online videos, it adapted Latent Factor Model (LFM) to categorize online videos. LFM enables us to add latent category feature to the basis of traditional recommendation system which comprised of dual user-item relationship. A series of experiments on YouTube review data were carried to prove that VRFCL algorithm achieves great effectiveness.

Key words: recommendation algorithm, online video, comment analysis, latent factor model, sentiment orientation

中图分类号:

TP181

尹路通, 于炯, 鲁亮, 英昌甜, 郭刚. 融合评论分析和隐语义模型的视频推荐算法[J]. 计算机应用, 2015, 35(11): 3247-3251.

YIN Lutong, YU Jiong, LU Liang, YING Changtian, GUO Gang. Video recommendation algorithm fusing comment analysis and latent factor model[J]. Journal of Computer Applications, 2015, 35(11): 3247-3251.

参考文献

[1] NIE B, ZHANG H, LIU Y. Social interaction based video recommendation: recommending YouTube videos to facebook users[C]// Proceedings of the 2014 IEEE Conference on Computer Communications Workshops. Piscataway: IEEE, 2014: 97-102.
[2] MEI T, YANG B, HUA X, et al.VideoReach: an online video recommendation system[C]// Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2007: 767-768.
[3] YOSHIDA T, IRIE G, ARAI H, et al.Towards semantic and affective content-based video recommendation[C]// Proceedings of the 2013 IEEE International Conference on Multimedia and Expo Workshops. Piscataway: IEEE, 2013: 1-6.
[4] DEMOVIC L, FRITSCHER E, KRIZ J, et al.Movie recommendation based on graph traversal algorithms[C]// Proceedings of the 2013 24th International Workshop on Database and Expert Systems Applications. Piscataway: IEEE, 2013: 152-156.
[5] YANG X, YU J, IBRAHIM T, et al.Collaborative filtering recommendation models considering item attributes[J]. Journal of Computer Applications, 2013, 33(11): 3062-3066.(杨兴耀, 于炯, 吐尔根·依布拉音,等. 考虑项目属性的协同过滤推荐模型[J]. 计算机应用, 2013, 33(11): 3062-3066.)
[6] HA I, OH K J, HONG M D, et al.Social filtering using social relationship for movie recommendation[C]// Proceedings of the 4th International Conference on Computational Collective Intelligence, Technologies and Applications. Berlin: Springer, 2012: 395-404.
[7] HUANG C R, LEE L H. Contrastive approach towards text source classification based on Top-Bag-of-Word similarity[C]// Proceedings of the 22nd Pacific Asia Conference on Language, Information and Computation. Manila: PACLIC, 2008: 404-410.
[8] RATNAPARKHI A. A maximum entropy model for part-of-speech tagging[C]// Proceedings of the 1996 Conference on Empirical Methods in Natural Language Processing. Philadelphia: EMNLP, 1996: 133-142.
[9] XUE G, DAI W, YANG Q, et al.Topic-bridged PLSA for cross-domain text classification[C]// Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2008: 627-634.
[10] FOULDS J, BOYLES L, DUBOIS C, et al.Stochastic collapsed variational Bayesian inference for latent Dirichlet allocation[C]// Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2013: 446-454.
[11] JIANG Y, DUMONT D M, PAIVA K A, et al.A latent class model to identify city/town chronic disease patterns[J]. Preventive Medicine, 2015,73: 139-144.
[12] O'CALLAGHAN D, HARRIGAN M, CARTHY J, et al.Network analysis of recurring YouTube spam campaigns[C]// Proceedings of the International Conference on Weblogs and Social Media. Dublin: ICWSM, 2012:531-534.
[13] HYNDMAN R J, KOEHLER A B. Another look at measures of forecast accuracy[J]. International Journal of Forecasting, 2006, 22(4): 679-688.
[14] HUANG C, YIN J,WANG J, et al.Uncertain neighbors' collaborative filtering recommendation algorithm[J]. Chinese Journal of Computers, 2010, 33(8): 1369-1377.(黄创光, 印鉴, 汪静, 等. 不确定近邻的协同过滤推荐算法 [J]. 计算机学报, 2010, 33(8): 1369-1377.)

[1]	刘欢, 李晓戈, 胡立坤, 胡飞雄, 王鹏华. 基于知识图谱驱动的图神经网络推荐模型[J]. 计算机应用, 2021, 41(7): 1865-1870.
[2]	林怿星, 唐华. 基于异构信息网络的混合推荐模型[J]. 计算机应用, 2021, 41(5): 1348-1355.
[3]	高铭蔚, 桑楠, 杨茂林. 基于胶囊网络的交互式网络电视视频点播推荐模型[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3171-3177.
[4]	任柯舟, 彭甫镕, 郭鑫, 王喆, 张晓静. 动态融合社交信息的社会化推荐[J]. 计算机应用, 2021, 41(10): 2806-2812.
[5]	杨书新, 张楠. 融合情感词典与上下文语言模型的文本情感分析[J]. 计算机应用, 2021, 41(10): 2829-2834.
[6]	杨璐, 何明祥. 基于门控机制和卷积神经网络的中文文本情感分析模型[J]. 计算机应用, 2021, 41(10): 2842-2848.
[7]	李翔锟, 贾彩燕. 融合重叠社区正则化及隐式反馈的协同过滤方法[J]. 计算机应用, 2021, 41(1): 53-59.
[8]	李春英, 汤庸, 肖政宏, 李天送. 学术社交网络中的权威学者推荐模型[J]. 计算机应用, 2020, 40(9): 2594-2599.
[9]	秦婧, 张青博, 王斌. 关注长尾物品的推荐方法[J]. 计算机应用, 2020, 40(2): 454-458.
[10]	张文龙, 钱付兰, 陈洁, 赵姝, 张燕平. 基于双重最相关注意力网络的协同过滤推荐算法[J]. 计算机应用, 2020, 40(12): 3445-3450.
[11]	孟仕林, 赵蕴龙, 关东海, 翟象平. 融合情感与语义信息的情感分析方法[J]. 计算机应用, 2019, 39(7): 1931-1935.
[12]	雷曼, 龚琴, 王纪超, 王保群. 基于标签权重的协同过滤推荐算法[J]. 计算机应用, 2019, 39(3): 634-638.
[13]	田保军, 杨浒昀, 房建东. 融合信任和基于概率矩阵分解的推荐算法[J]. 计算机应用, 2019, 39(10): 2834-2840.
[14]	文凯, 朱传亮. 融合社交网络和兴趣的正则化矩阵分解推荐模型[J]. 计算机应用, 2018, 38(9): 2523-2528.
[15]	杨帅, 王鹃. 基于堆栈降噪自编码器改进的混合推荐算法[J]. 计算机应用, 2018, 38(7): 1866-1871.

融合评论分析和隐语义模型的视频推荐算法

Video recommendation algorithm fusing comment analysis and latent factor model

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