可扩展的融合多源异构数据的推荐模型

doi:10.13190/j.jbupt.2020-229

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (3): 106-111.doi: 10.13190/j.jbupt.2020-229

可扩展的融合多源异构数据的推荐模型

冀振燕¹, 吴梦丹^1,2, 杨春¹, 李俊东¹

1. 北京交通大学软件学院, 北京 100044;
2. 中国科学院软件研究所, 北京 100190

收稿日期:2020-11-12 出版日期:2021-06-28 发布日期:2021-06-23
作者简介:冀振燕(1972-),女,副教授,博士生导师,E-mail:zhyji@bjtu.edu.cn.
基金资助:
国家重点研究发展计划项目（2018YFC0809300）；国家自然科学基金项目（51935002）

Scalable Recommendation Models Fusing Multi-Source Heterogeneous Data

JI Zhen-yan¹, WU Meng-dan^1,2, YANG Chun¹, LI Jun-dong¹

1. School of Software Engineering, Beijing Jiaotong University, Beijing 100044, China;
2. Institute of Software, Chinese Academy of Sciences, Beijing 100190, China

Received:2020-11-12 Online:2021-06-28 Published:2021-06-23

摘要/Abstract

摘要： 社交关系在生活中扮演着重要角色，用户通常会受到其好友偏好的影响，更容易选择好友购买过的物品.为了解决推荐系统冷启动问题，对融合社交关系的推荐系统进行了研究，提出了贝叶斯个性化排序评论评分社交模型和可扩展的贝叶斯个性化排序评论评分社交模型，将评分、评论、社交关系等多源异构数据从数据源层面进行了融合，通过用户好友信任度模型将社交关系引入到推荐系统中，用基于段向量的分布式词袋模型处理评论，用全连接神经网络处理评分，用改进的贝叶斯个性化排序模型对排序结果进行优化.实验在Yelp公开数据集上进行了实验，实验结果表明，所提出的2种模型的推荐准确度均优于其他推荐模型.

关键词: 推荐系统, 多源异构数据, 社交关系, 混合模型, 数据融合

Abstract: Social relationship plays an important role in life, and users are often affected by their friends' preferences. It is easier for users to choose items that their friends have purchased. In order to solve the cold start problem of the recommended system, a recommendation system that integrates social relationships is studied, and Bayesian personalized ranking review score social model and scalable Bayesian personalized ranking review score social model are proposed. The proposed fusion recommendation models integrate multi-source heterogeneous data such as scores, reviews, and social relationships from the data source level, introduce social relationships into the recommendation system through the user friend trust model, use the paragraph vector-distributed memory model to process review, use the fully connected neural network to process rating, and use an improved Bayesian personalized ranking model to optimize the ranking results. Experiments are conducted on the Yelp public dataset. It is shown that the recommendation accuracy of the two proposed models are better than other recommendation models.

Key words: recommendation system, multi-source heterogeneous data, social relation, hybrid model, data fusion

中图分类号:

TP391

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.

JI Zhen-yan, WU Meng-dan, YANG Chun, LI Jun-dong. Scalable Recommendation Models Fusing Multi-Source Heterogeneous Data[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(3): 106-111.

参考文献

[1] Fabbri F, Bonchi F, Boratto L, et al. The effect of homophily on disparate visibility of minorities in people re-commender systems[C]//International AAAI Conference on Web and Social Media.[S.l.]:AAAI, 2020:165-175.
[2] Gao Jingyue, Wang Xiting, Wang Yasha, et al. Explainable recommendation through attentive multi-view learning[C]//AAAI Conference on Artificial Intelligence. Hawaii:AAAI, 2019:3622-3629.
[3] Ji Zhenyan, Pi Huaiyu, Wei Wei, et al. Recommendation based on review texts and social communities:a hybrid model[J]. IEEE Access, 2019, 7:40416-40427.
[4] Wang Chengwei, Zhou Tengfei, Chen Chen, et al. Camo:a collaborative ranking method for content based recommendation[C]//AAAI Conference on Artificial Intelligence. Hawaii:AAAI, 2019:5224-5231.
[5] 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.
[6] Liu Hao, Li Ting, Hu Renjun, et al. Joint representation learning for multi-modal transportation recommendation[C]//AAAI Conference on Artificial Intelligence. Hawaii:AAAI, 2019:1036-1043.
[7] Zheng Lei, Noroozi V, Yu P S. Joint deep modeling of users and items using reviews for recommendation[C]//Tenth ACM International Conference on Web Search and Data Mining. Cambridge:ACM, 2017:425-434.
[8] Chen Wei, Niu Zhengdong, Zhao Xiangyu, et al. A hybrid recommendation algorithm adapted in e-learning environments[J]. World Wide Web, 2014, 17(2):271-284.
[9] Zhang Shuai, Yao Lina, Sun Aixin, et al. Deep learning based recommender system:a survey and new perspectives[J]. ACM Computing Surveys (CSUR), 2019, 52(1):1-38.
[10] Milgram, Stanley. The small world problem[J]. Psychology Today, 1967, 2(1):60-67.
[11] Elkahky A M, Song Y, He X. A multi-view deep learning approach for cross domain user modeling in recommendation systems[C]//24th International Conference on World Wide Web. Florence:WWW, 2015:278-288.
[12] Krohn-Grimberghe A, Drumond L, Freudenthaler C, et al. Multi-relational matrix factorization using Bayesian personalized ranking for social network data[C]//Fifth ACM International Conference on Web Search and Data Mining. Washington:WSDM, 2012:173-182.
[13] Le Q, Mikolov T. Distributed representations of sentences and documents[C]//International Conference on Machine Learning. Beijing:ICML, 2014:1188-1196.
[14] Rendle S, Freudenthaler C, Gantner Z, et al. BPR:Bayesian personalized ranking from implicit feedback[EB/OL]. 2012(2012-05-09)[2020-11-12]. https://arxiv.org/abs/1205.2618.
[15] Al-Mashari, Majed, Zairi M. Revisiting BPR:a holistic review of practice and development[J]. Business Process Management Journal, 2000, 6(1):10-42.
[16] He R, McAuley J. VBPR:visual Bayesian personalized ranking from implicit feedback[C]//AAAI Conference on Artificial Intelligence. Arizona:AAAI, 2016:144-150.

可扩展的融合多源异构数据的推荐模型

Scalable Recommendation Models Fusing Multi-Source Heterogeneous Data

RichHTML

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

本文评价

[1]	杜茂康彭俊杰胡勇进肖玲. 满足差分隐私的逻辑回归矩阵分解推荐算法[J]. 北京邮电大学学报, 2023, 46(3): 115-120.
[2]	张华强, 刘林, 秦昌礼, 陈雨, 苏庆华. 基于分布式惯导测量的机翼弹性形变算法[J]. 北京邮电大学学报, 2021, 44(6): 33-39,66.
[3]	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.
[4]	王永, 尹恩民, 冉珣. 基于BC聚类的差分隐私保护推荐算法[J]. 北京邮电大学学报, 2021, 44(2): 81-88.
[5]	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.
[6]	王雅青, 郭彩丽, 楚云霏, 周洪弘, 冯春燕. 面向会话型推荐系统的个性化分层循环模型[J]. 北京邮电大学学报, 2019, 42(6): 142-148.
[7]	孙朝宇, 高守婉, 杨旭, 陈朋朋, 牛强. 基于信道状态信息的矿难人员检测研究[J]. 北京邮电大学学报, 2019, 42(4): 96-101.
[8]	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.
[9]	余修武, 刘琴, 李向阳, 张可, 肖人榕. 基于改进蚁群的BP神经网络WSN数据融合算法[J]. 北京邮电大学学报, 2018, 41(4): 91-96.
[10]	晁浩, 鲁保云, 刘永利, 刘志中, 宋成. 基于谱信息熵和互补模型的声效模式检测[J]. 北京邮电大学学报, 2018, 41(2): 56-61.
[11]	张羽, 李更祥, 张鹏飞, 韦琳哲, 刘纪元. 基于多传感器数据融合的合成孔径声纳运动补偿算法[J]. 北京邮电大学学报, 2017, 40(5): 82-86.
[12]	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.
[13]	许建, 杨庚, 陈正宇, 王海勇, 王倩倩. 基于信源编码的可恢复数据融合隐私保护方案[J]. 北京邮电大学学报, 2016, 39(6): 67-71.
[14]	晁浩, 宋成, 刘志中. 基于元音模板匹配的声效多级检测[J]. 北京邮电大学学报, 2016, 39(4): 98-102.
[15]	蔡国永, 张东, 林煜明, 文益民. 面向推荐多样性改进的概率传播模型[J]. 北京邮电大学学报, 2016, 39(3): 34-38.