社交电商中融合信任和声誉的图神经网络推荐研究

doi:10.16381/j.cnki.issn1003-207x.2021.0708

中国管理科学 ›› 2021, Vol. 29 ›› Issue (10): 202-212.doi: 10.16381/j.cnki.issn1003-207x.2021.0708

• 论文 • 上一篇

社交电商中融合信任和声誉的图神经网络推荐研究

胡春华^1,2，邓奥¹,²，童小芹^1,2，缪和^1,2，王宗润³

1.湖南工商大学大数据与互联网创新研究院，湖南长沙410205；2.移动商务智能湖南省重点实验室，湖南长沙410205； 3.中南大学商学院，湖南长沙410083

收稿日期:2021-04-11 修回日期:2021-05-09 出版日期:2021-10-20 发布日期:2021-10-21
通讯作者: 胡春华(1973-)，男(汉族)，湖南娄底人，湖南工商大学，教授，博士(后)，教育部新世纪人才，研究方向：商务智能、大数据分析、个性化推荐等，Email：huch@hutb.edu.cn. E-mail:huch@hutb.edu.cn
基金资助:
国家自然科学基金面上资助项目(72072053)；国家自然科学基金重大资助项目(72091515)；湖南创新型省份建设专项（2019GK2131）

A Graph Neural Network Recommendation Study Combining Trust and Reputation in Social E-commerce

HU Chunhua^1,2, DENG Ao^1,2, TONG Xiaoqin^1,2, MIAO He^1,2, WANG Zongrun³

1. Research Institute of Big Data and Internet Innovation, Hunan Technology and Business University, Changsha 410205, China; 2. Key Laboratory of Hunan Province for Mobile Business Intelligence, Changsha 410205, China；3. School Business, Central South University, Changsha 410083, China

Received:2021-04-11 Revised:2021-05-09 Online:2021-10-20 Published:2021-10-21

摘要/Abstract

摘要： 社交电商可依据用户间的社交关系为用户提供感兴趣的商品或服务。现有研究多基于社会信任或社会声誉进行推荐，却忽略了信任与声誉间的相互作用，导致推荐效果欠理想。针对以上问题，本文提出了一种融合信任(Trust)和社会声誉(Social Reputation)的图神经网络推荐算法(TSR-GM)，采用社会声誉来深度刻画用户关系在推荐系统中的作用，利用社交网络中用户被信任程度对用户声誉进行排名，以图神经网络量化整合用户信任与声誉，并将结合后的新矩阵不断校正以获取更准确的用户信任，以此对矩阵分解后得到的新评分模型更新，最终得到更准确度量的预测评分矩阵。运用Epinions数据集开展的相关实验表明：与同类方法比，TSR-GM算法对提高推荐精度有较好效果。

关键词: 信任关系, 社会声誉, 图神经网络, 社交电商, 推荐系统

Abstract: Amid rapid development of social network, growing number of users leads to excessive information, challenging the beneficiaries in theory to filter the valuable bits. One question raised along this, which requires users to identify trustworthy content, presents researchers with the idea of studying the role of which trust relations among users play in social e-commerce. Some exploring in this field sees a connection between item ratings and trust relations of users, however, there often lacks integrity in reliable trust relation data, and even those that doesn’t show great disparity. Hence, a method to identify content and information that users trusted more swiftly and precisely is still in great demand. Also, researchers show increasing interest in the position that user reputation played in effecting user trust and how to merge those two to offer more satisfying recommendation.

Key words: trust relationship, social reputation, graph neural network, social commerce, recommendation system

中图分类号:

F224

胡春华,邓奥,童小芹,缪和,王宗润. 社交电商中融合信任和声誉的图神经网络推荐研究[J]. 中国管理科学, 2021, 29(10): 202-212.

HU Chunhua, DENG Ao, TONG Xiaoqin, MIAO He, WANG Zongrun. A Graph Neural Network Recommendation Study Combining Trust and Reputation in Social E-commerce[J]. Chinese Journal of Management Science, 2021, 29(10): 202-212.

参考文献

[1] Li Chiaying, Ku Yicheng. The power of a thumbs-up: Will e-commerce switch to social commerce [J] . Information & Management, 2018, 55(3): 340- 357.
[2] 艾媒研究院. 2020-2021年中国移动社交行业年度研究报告 [R] , Working Paper, 艾媒大文娱产业研究中心, 2020.AI Media Research Institute. Annual research report on China’s mobile social industry from 2020 to 2021 [R] , Working Paper,Research Center for entertainment industry of aimedia, 2020.
[3] Li Yungming, Wu Chunte, Lai Chengyang. A social recommender mechanism for e-commerce: Combining similarity, trust, and relationship [J] . Decision Support Systems, 2013, 55(3): 740-752.
[4] Belkhadir I, Omar E D, Boumhidi J. An intelligent recommender system using social trust path for recommendations in web-based social networks [J] . Procedia Computer Science, 2019, 148(3): 181- 190.
[5] Zhu Yunqiang, Zhu A-Xing, Feng Min, et al. A similarity-based automatic data recommendation approach for geographic models [J] . International Journal of Geographical Information Systems, 2017, 31(7): 1403-1424.
[6] Modarresi K. Recommendation system based on complete personalization [J] . Procedia Computer Science, 2016, 80(5): 2190-2204.
[7] Xue Leyang, Zhang Peng, Zeng An. Enhancing the long-term performance of recommender system [J] . Physica A: Statistical Mechanics and its Applications, 2019, 531(10): 121731-121742.
[8] Li Gai, Chen Youfen, Zhang Zhiqiang Q, et al. Social personalized ranking with both the explicit and implicit reputation of user trust and of item ratings [J] . Engineering Applications of Artificial Intelligence, 2018, 67(1): 283-295.
[9] Lu Qibei, Guo Feipeng. Personalized information recommendation model based on context contribution and item correlation [J] . Measurement, 2019, 142(8): 30-39.
[10] Moradi P, Ahmadian S. A reliability-based recommendation method to improve trust-aware recommender systems [J] . Expert Systems with Applications, 2015, 42(21): 7386-7398.
[11] Du X, Ge S, Wang N, et al. Personalized product service scheme recommendation based on trust and cloud model [J] . IEEE Access, 2020, PP(99): 1-1.
[12] Ma Xiao, Lu Hongwei, Gan Zaobin, et al. An explicit trust and distrust clustering based collaborative filtering recommendation approach [J] . Electronic Commerce Research and Applications, 2017, 25(10): 29-39.
[13] Hwang W S, Lee H J, Kim S W, et al. Efficient recommendation methods using category experts for a large dataset [J] . Information Fusion, 2016, 28(C): 75-82.
[14] 景楠, 王建霞, 许皓,等. 基于用户社会关系的社交网络好友推荐算法研究 [J] . 中国管理科学, 2017, 25(3): 164-171.Jing Nan, Wang Jianxia, Xu Hao, et al. Research on social network friend recommendation algorithm based on user social relationship [J] . Chinese Journal of Management Science, 2017, 25(3): 164-171.
[15] 尹进, 胡祥培, 郑毅,等. 社会化商务中基于经验及推荐的消费者感知信任模糊融合模型 [J] . 中国管理科学, 2020, 28(1): 122-133.Yin Jin, Hu Xiangpei, Zheng Yi, et al. Fuzzy fusion model of consumer perception and trust based on experience and recommendation in social commerce [J] . Chinese Journal of Management Science, 2020, 28(1): 122-133.
[16] 李志宏, 庄云蓓. 基于水军信任惩罚的多维用户影响力度量模型 [J] . 系统工程理论与实践, 2017, 37(7): 1820-1832.Li Zhihong, Zhuang Yunbei. Multidimensional user influence measurement model based on trust punishment of Navy [J] . Systems Engineering Theory and Practice Systems, 2017, 37(7): 1820-1832.
[17] Dey S, Sen S K. Trust evaluation model in cloud using reputation, recommendation and QOS based approach [C] // Proceedings of 2018 International Conference on Research in Intelligent and Computing in Engineering, San Salvador, El Salvador, August 22-24, 2018.
[18] 胡春华, 童小芹, 梁伟. 基于信任和不信任关系的实值受限玻尔兹曼机推荐算法 [J] .系统工程理论与实践, 2019, 39(7): 1817-1830.Hu Chunhua, Tong Xiaoqin, Liang Wei. Real valued restricted boltzmann machine recommendation algorithm based on trust and distrust relationship [J] . Systems Engineering Theory and Practice Systems, 2017, 37(7): 1820-1832.
[19] Barber B, Gambetta D. Trust: Making and breaking cooperative relations [J] . Contemporary Sociology, 1992, 21(3): 401.
[20] Abdul-Rahman A, Hailes S. Supporting trust in virtual communities [C] // Proceedings of the 33rd Annual Hawaii International Conference on System Sciences, IEEE Computer Society, Maui, Hawaii, January 4-7, 2000.
[21] Wang Xiang， He Xiangnan, Wang Meng, et al. Neural graph collaborative filtering [J] . ACM, 2019, 19(7): 21-25.
[22] Wu Shiwen, Zhang Wentao, Sun Fei, et al. Graph neural networks in recommender systems: A survey [J] . arXiv preprint arXiv: 2011.02260, 2020.
[23] He Xiangnan, Liao Lizi, Zhang Hanwang, et al. Neural collaborative filtering [C] //Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, April 3-7, ACM, 2017: 173-182.
[24] Ma hao, Yang Haixuan, Lyu M R, et al. Sorec: social recommendation using probabilistic matrix factorization [C] // Proceedings of the 17th ACM Conference on Information and Knowledge Management, Calofornia, USA, October, ACM, 2008: 931-940.
[25] Georgiev K, Nakov P. A non-IID framework for collaborative filtering with restricted boltzmann machines [C] //International Conference on Machine Learning, Atlanta, USA, June 17-19, Proceedings of Machine Learning Research, 2013: 1148-1156.
[26] Yang Bo, Lei Yu, Liu Dayou, et al. Social collaborative filtering by trust [J] . IEEE transactions on pattern analysis and machine intelligence, 2016, 39(8): 1633-1647.
[27] Zhao Jianli, Wang Wei, Zhang Zipei, et al. TrustTF: A tensor factorization model using user trust and implicit feed- back for context-aware recommender systems [J] . Knowledge-Based Systems, 2020. DOI:10.1016/j.knosys.2020.106434.
[28] Ahmed A, Saleem K, Rashid U, et al. Modeling trust-aware recommendations with temporal dynamics in social networks [J] . IEEE Access, 2020, PP(8): 149676-149705.
[29] 邓晓懿, 金淳, 韩庆平,等. 基于情境聚类和用户评级的协同过滤推荐模型 [J] . 系统工程理论与实践, 2013, 33(11): 2945-2953.Deng Xiaoyi, Jin Chun, Han Qingping, et al. Collaborative filtering recommendation model based on context clustering and user rating [J] . Systems Engineering Theory and Practice Systems, 2013, 33(11): 2945-2953.

社交电商中融合信任和声誉的图神经网络推荐研究

A Graph Neural Network Recommendation Study Combining Trust and Reputation in Social E-commerce

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

Metrics

本文评价

推荐阅读 0

[1]	金飞飞,刘金培，陈华友，杜鹏程. 基于信任关系和信息测度的概率语义社会网络群决策模型[J]. 中国管理科学, 2021, 29(10): 178-190.
[2]	胡春华, 赵慧, 童小芹, 任剑. 推荐系统对消费者网购支出的影响研究[J]. 中国管理科学, 2020, 28(6): 158-170.
[3]	梁昌勇, 冷亚军, 王勇胜, 戚筱雯. 电子商务推荐系统中群体用户推荐问题研究[J]. 中国管理科学, 2013, 21(3): 153-158.