融合多源异构数据的混合推荐模型

doi:10.13190/j.jbupt.2018-176

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (1): 126-132.doi: 10.13190/j.jbupt.2018-176

融合多源异构数据的混合推荐模型

冀振燕, 皮怀雨, 姚伟娜

北京交通大学软件学院, 北京 100044

收稿日期:2018-08-04 出版日期:2019-02-28 发布日期:2019-03-08
作者简介:冀振燕(1972-),女,副教授,E-mail:zhyji@bjtu.edu.cn.
基金资助:
国家自然科学基金项目（61272353）；中央高校基本科研业务费专项资金（2017YJS215）

A Hybrid Recommendation Model Based on Fusion of Multi-Source Heterogeneous Data

JI Zhen-yan, PI Huai-yu, YAO Wei-na

School of Software Engineering, Beijing Jiaotong University, Beijing 100044, China

Received:2018-08-04 Online:2019-02-28 Published:2019-03-08

摘要/Abstract

摘要： 为更全面地反映用户个人偏好，提高推荐的准确度，提出了一种融合多源异构数据的混合推荐模型.综合考虑了用户社交关系和用户评论对用户评分的影响，从评论中提取主题信息作为用户和商家的特征，采用社区发现算法为用户划分社区，利用机器学习方法为社区建立模型，预测用户对商家的评分，再根据评分对商家进行排序，取前N个商家推荐给用户.实验结果表明，提出的混合推荐模型与经典推荐算法相比，可提高评分预测的准确度，从而提高推荐的准确度.

关键词: 社交关系, 评论, 评分, 推荐模型

Abstract: In order to reflect users' personalized preferences more comprehensively and improve the accuracy of recommendation, a hybrid recommendation model based on fusion of multi-source heterogeneous data is proposed. This model takes the impacts from both users' social relationships and reviews on ratings into account. Topics are extracted from reviews as user features and business features, and then communities are divided for users via a community discovery algorithm. Finally, a machine learning algorithm is used to model user communities in order to predict ratings. Businesses are ranked based on predicted ratings and then the top N businesses are recommended to the user. The experimental results show that the proposed hybrid recommendation model can improve the rating prediction accuracy and recommendation accuracy compared with the conventional recommendation algorithms.

Key words: social relationships, reviews, ratings, recommendation model

中图分类号:

TN911.22

冀振燕, 皮怀雨, 姚伟娜. 融合多源异构数据的混合推荐模型[J]. 北京邮电大学学报, 2019, 42(1): 126-132.

JI Zhen-yan, PI Huai-yu, YAO Wei-na. A Hybrid Recommendation Model Based on Fusion of Multi-Source Heterogeneous Data[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(1): 126-132.

参考文献

[1] 王永, 邓江洲. 基于KL散度的用户相似性协同过滤算法[J]. 北京邮电大学学报, 2017, 40(2):110-114. Wang Yong, Deng Jiangzhou. User similarity collaborative filtering algorithm based on KL divergence[J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40(2):110-114.
[2] 王晓军, 付超. 利用模糊分块改进协同过滤的扩展性和准确性[J]. 北京邮电大学学报, 2017, 40(1):74-78. Wang Xiaojun, Fu Chao. Enhancing scalability and accuracy of collaborative filtering using fuzzy blocking[J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40(1):74-78.
[3] Dziugaite G K, Roy D M. Neural network matrix factorization[EB/OL]. (2015-12-10). https://arxiv.org/abs/1511.06443.
[4] He Xiangnan, Liao Lizi, Zhang Hanwang, et al. Neural collaborative filtering[C]//WWW'17 Proceedings of the 26th International Conference on World Wide Web. New York:ACM, 2017:173-182.
[5] Xu Yunhong, Zuo Xianli. A LDA model based text-mining method to recommend reviewer for proposal of research project selection[C]//International Conference on Service Systems and Service Management. New York:IEEE, 2016:1-5.
[6] Mcauley J, Leskovec J. Hidden factors and hidden topics:understanding rating dimensions with review text[C]//Proceedings of the 7^th ACM Conference on Recommender System. New York:ACM, 2013:165-172.
[7] Takuma K, Yamamoto J, Kamei S, et al. A hotel recommendation system based on reviews:what do you attach importance to?[C]//International Symposium on Computing and Networking. New York:IEEE, 2016:710-712.
[8] Zhang Yongfeng, Lai Guokun, Zhang Min, et al. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis[C]//Proceedings of the 37^th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM, 2014:83-92.
[9] Xu Yinqing, Lam W, Lin Tianyi. Collaborative filtering incorporating review text and co-clusters of hidden user communities and item groups[C]//Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. New York:ACM, 2014:251-260.
[10] Shen Xiaoxuan, Yi Baolin, Zhang Zhaoli, et al. Automatic recommendation technology for learning resources with convolutional neural network[C]//International Symposium on Educational Technology. New York:IEEE, 2016:30-34.
[11] Jamali M, Ester M. A matrix factorization technique with trust propagation for recommendation in social networks[C]//Proceedings of the fourth ACM conference on Recommender Systems. New York:ACM, 2010:135-142.
[12] Ma Hao, Yang Haixuan, Lyu M R, et al. SoRec:social recommendation using probabilistic matrix factorization[C]//Proceedings of the 17^th ACM Conference on Information and Knowledge Management. New York:ACM, 2008:931-940.
[13] Guo Guibing, Zhang Jie, Yorke-Smith N. TrustSVD:collaborative filtering with both the explicit and implicit influence of user trust and of item ratings[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence. New York:ACM, 2015:123-129.
[14] Deng Shuiguang, Huang Longtao, Xu Guandong, et al. On deep learning for trust-aware recommendations in social networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(5):1164-1177.
[15] Ma Haojie, Che Ddongsheng. An integrative social network and review content based recommender system[J]. Journal of Industrial and Intelligent Information, 2016, 4(1):69-75.
[16] 黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41(7):191-219. Huang Liwei, Jiang Bitao, Lu Shouye, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Computers, 2018, 41(7):191-219.
[17] Hoffman M D, blei D M, Bach B. Online learning for latent dirichlet allocation[C]//International Conference on Neural Information Processing Systems. Berlin:Springer, 2010:856-864.
[18] Clauset A, Newman M E J, Moore C. Finding community structure in very large networks[J]. Physical Review E, 2004, 70(6 Pt 2):066111.

融合多源异构数据的混合推荐模型

A Hybrid Recommendation Model Based on Fusion of Multi-Source Heterogeneous Data

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	张栋, 陈鸿龙. 融合文本信息的轻量级图卷积网络推荐模型[J]. 北京邮电大学学报, 2021, 44(5): 88-93.
[2]	刘国桢, 陈鸿龙. 卷积记忆图协同过滤[J]. 北京邮电大学学报, 2021, 44(3): 21-26.
[3]	冀振燕, 吴梦丹, 杨春, 李俊东. 可扩展的融合多源异构数据的推荐模型[J]. 北京邮电大学学报, 2021, 44(3): 106-111.
[4]	冀振燕, 宋晓军, 皮怀雨, 杨春. 基于深度学习的融合多源异构数据的推荐模型[J]. 北京邮电大学学报, 2019, 42(6): 35-42.
[5]	刘占峰, 潘甦. 基于模糊粗糙集实例选择的混合算法在信用评分中的应用[J]. 北京邮电大学学报, 2019, 42(2): 101-107.
[6]	苏放, 王晓宇, 张治. 基于注意力机制的评论摘要生成[J]. 北京邮电大学学报, 2018, 41(3): 7-13.
[7]	王永, 邓江洲. 基于KL散度的用户相似性协同过滤算法[J]. 北京邮电大学学报, 2017, 40(2): 110-114.
[8]	卢美莲, 张正林, 刘智超. MFWT:一种推荐学术论文的混合模型[J]. 北京邮电大学学报, 2016, 39(4): 24-29.
[9]	杨恒宇, 李慧宗, 林耀进, 张佳. 协同过滤中有影响力近邻的选择[J]. 北京邮电大学学报, 2016, 39(1): 29-34.
[10]	蔡国永, 吕瑞, 樊永显. 基于标签和因子分析的协同推荐方法[J]. 北京邮电大学学报, 2015, 38(3): 34-38.
[11]	胡楠，袁庆升，魏更宇，黄玮，杨义先. 利用会话模式的垃圾电话检测[J]. 北京邮电大学学报, 2011, 34(1): 130-134.
[12]	张玉洁,孟祥武. 不同电信欠费率下信用评分问题[J]. 北京邮电大学学报, 2010, 33(6): 88-92.
[13]	张玉洁;孟祥武. 利用蚁群算法求解电信客户初始信用评分问题[J]. 北京邮电大学学报, 2010, 33(1): 124-128.