融合异质网络与主题模型的方面分预测

doi:10.11772/j.issn.1001-9081.2017.11.3201

计算机应用 ›› 2017, Vol. 37 ›› Issue (11): 3201-3206.DOI: 10.11772/j.issn.1001-9081.2017.11.3201

• 2017年中国计算机学会人工智能会议(CCFAI 2017) • 上一篇下一篇

融合异质网络与主题模型的方面分预测

吉余岗^1,2, 李依桐^1,2, 石川^1,2

1. 北京邮电大学计算机学院, 北京 100876;
2. 智能通信软件与多媒体北京市重点实验室(北京邮电大学), 北京 100876

收稿日期:2017-05-11 修回日期:2017-05-31 出版日期:2017-11-10 发布日期:2017-11-11
通讯作者: 石川
作者简介:吉余岗(1993-),男,江苏泰州人,博士研究生,CCF会员,主要研究方向:数据挖掘、机器学习;李依桐(1992-),女,北京人,硕士,主要研究方向:数据挖掘、机器学习;石川(1978-),男,北京人,教授,博士,CCF会员,主要研究方向:数据挖掘、机器学习、演化计算。
基金资助:
国家自然科学基金资助项目（61375058）；国家973计划项目（2013cb329606）；北京市教育委员会共建项目。

Aspect rating prediction based on heterogeneous network and topic model

JI Yugang^1,2, LI Yitong^1,2, SHI Chuan^1,2

1. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia(Beijing University of Posts and Telecommunications), Beijing 100876, China

Received:2017-05-11 Revised:2017-05-31 Online:2017-11-10 Published:2017-11-11
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61375058), the National Basic Research Program (973 Program) of China (2013cb329606), the Co-construction Project of Beijing Municipal Commission of Education.

摘要/Abstract

摘要： 针对传统方面分预测模型只考虑内容信息而缺乏对评论网络结构的分析，提出了融合异质信息网络和主题模型构建方面分预测算法（HINToAsp）。首先，从意见短语角度构建了评论主题挖掘模型（Phrase-PLSA），有效整合评论信息和评分信息进行方面主题挖掘；进而，考虑用户、评论和商品之间的结构信息，提出了在"用户-评论-商品"异质信息网络上的主题传播模型模型，用于刻画用户特性、商品属性；最后，基于随机游走框架有效整合内容信息和结构信息，进行精准的方面分预测。通过在大众点评（Dianping）和TripAdvisor数据集上和四元组PLSA （QPLSA）、高斯分布的情绪评估（GRAOS）模型及情绪均衡主题模型（SATM）的准确度对比实验，证明了HINToAsp算法的有效性，可以更好地用于商品的推荐系统。

关键词: 方面分预测, 异质信息网络, 主题模型, 结构信息, 推荐系统

Abstract: Concerning the problem that traditional aspect rating prediction methods just pay attention to textual information while ignoring the structural information in the review network, a novel Aspect rating prediction method based on Heterogeneous Information Network and Topic model (HINToAsp) was proposed for effectively integering textual information and structural information. Firstly, a new review topic model of opinion phrases called Phrase-PLSA (Phrase-based Probabilistic Latent Semantic Analysis) was put forward to integrate textual information of reviews and ratings for mining aspect topics. And then, considering the rich structural information among users, reviews, and items, a topic propagation model was designed by the aid of constructing "User-Review-Item" heterogeneous information network. Finally, a random walk framework was used to combine textual information and structural information effectively, which insured an accurate aspect rating prediction. The experimental results on both Dianping corpora and TripAdvisor corpora demonstrate that HINToAsp is more effective than recent methods like the Quad-tuples PLSA (QPLSA) model, the Gaussian distribution for RAting Over Sentiments (GRAOS) model and the Sentiment-Aligned Topic Model (SATM), and has better performance on recommendation system.

Key words: aspect rating prediction, Heterogeneous Information Network (HIN), topic model, structural information, recommendation system

中图分类号:

TP391

吉余岗, 李依桐, 石川. 融合异质网络与主题模型的方面分预测[J]. 计算机应用, 2017, 37(11): 3201-3206.

JI Yugang, LI Yitong, SHI Chuan. Aspect rating prediction based on heterogeneous network and topic model[J]. Journal of Computer Applications, 2017, 37(11): 3201-3206.

参考文献

[1] MOGHADDAM S, ESTER M. On the design of LDA models for aspect-based opinion mining[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management. New York:ACM, 2012:803-812.
[2] 林晓勇, 代苓苓, 史晟辉, 等. 基于主题模型的矩阵分解推荐算法[J]. 计算机应用, 2015, 35(S2):122-124.(LIN X Y, DAI L L, SHI S H, et al. Matrix factorization recommendation based on topic model[J]. Journal of Computer Applications, 2015, 35(S2):122-124.)
[3] 王春龙, 张敬旭. 基于LDA的改进K-means算法在文本聚类中的应用[J]. 计算机应用, 2014, 34(1):249-254. (WANG C L, ZHANG J X. Improved K-means algorithm based on latent Dirichlet allocation for text clustering[J]. Journal of Computer Applications, 2014, 34(1):249-254.)
[4] HOFMANN T. Probabilistic latent semantic indexing[C]//Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 1999:50-57.
[5] BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3(1):993-1022.
[6] LU Y, ZHAI C X, SUNDARESAN N. Rated aspect summarization of short comments[C]//Proceedings of the 18th International Conference on World Wide Web. New York:ACM, 2009:131-140.
[7] SUN Y, HAN J, ZHAO P, et al. RankClus:integrating clustering with ranking for heterogeneous information network analysis[C]//Proceedings of the 12th International Conference on Extending Database Technology:Advances in Database Technology. New York:ACM, 2009:565-576.
[8] SHI C, LI Y, ZHANG J, et al. A survey of heterogeneous information network analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(1):17-37.
[9] ZHENG X, LIN Z, WANG X, et al. Incorporating appraisal expression patterns into topic modeling for aspect and sentiment word identification[J]. Knowledge-Based Systems, 2014, 61(2):29-47.
[10] WANG H, LU Y, ZHAI C X. Latent aspect rating analysis without aspect keyword supervision[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2011:618-626.
[11] WANG H, ESTER M. A sentiment-aligned topic model for product aspect rating prediction[EB/OL].[2016-11-20]. http://www.anthology.aclweb.org/D/D14/D14-1126.pdf.
[12] LI Y, SHI C, ZHAO H, et al. Aspect mining with rating bias[C]//Proceedings of the 2016 Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin:Springer International Publishing, 2016:458-474.
[13] SHI C, ZHOU C, KONG X, et al. HeteRecom:a semantic-based recommendation system in heterogeneous networks[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2012:1552-1555.
[14] YU X, REN X, SUN Y, et al. Personalized entity recommendation:a heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York:ACM, 2014:283-292.
[15] SUN Y, HAN J. Mining heterogeneous information networks:a structural analysis approach[J]. ACM SIGKDD Explorations Newsletter, 2013, 14(2):20-28.
[16] 张邦佐, 桂欣, 何涛,等. 一种融合异构信息网络和评分矩阵的推荐新算法[J]. 计算机研究与发展, 2014, 51(S2):69-75.(ZHANG B Z, GUI X, HE T, et al. A novel recommender algorithm on fusion heterogeneous information network and rating matrix[J]. Journal of Computer Research and Development, 2014, 51(S2):69-75.)
[17] LUO W, ZHUANG F, ZHAO W, et al. QPLSA:Utilizing quad-tuples for aspect identification and rating[J]. Information Processing and Management, 2015, 51(1):25-41.
[18] LUO W, ZHUANG F, CHENG X, et al. Ratable aspects over sentiments:predicting ratings for unrated reviews[C]//Proceedings of the 2014 IEEE International Conference on Data Mining. Piscataway, NJ:IEEE, 2014:380-389.

融合异质网络与主题模型的方面分预测

Aspect rating prediction based on heterogeneous network and topic 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

[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]	杨丰瑞, 霍娜, 张许红, 韦巍. 基于注意力机制的主题扩展情感对话生成[J]. 计算机应用, 2021, 41(4): 1078-1083.
[4]	车冰倩, 周栋. 融合网络结构信息及文本内容的标签推荐方法[J]. 计算机应用, 2021, 41(4): 976-983.
[5]	李凯, 李洁. 基于pinball损失的结构模糊多分类支持向量机算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3104-3112.
[6]	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.
[7]	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.
[8]	杨威亚, 余正涛, 高盛祥, 宋燃. 基于跨语言神经主题模型的汉越新闻话题发现方法[J]. 计算机应用, 2021, 41(10): 2879-2884.
[9]	朱思淼, 魏世伟, 魏思恒, 余敦辉. 基于弹幕情感分析和主题模型的视频推荐算法[J]. 计算机应用, 2021, 41(10): 2813-2819.
[10]	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.
[11]	尹春勇, 章荪. 面向短文本情感分类的端到端对抗变分贝叶斯方法[J]. 计算机应用, 2020, 40(9): 2536-2542.
[12]	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.
[13]	田保军, 刘爽, 房建东. 融合主题信息和卷积神经网络的混合推荐算法[J]. 计算机应用, 2020, 40(7): 1901-1907.
[14]	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.
[15]	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.