融合商品流行度与信任度的混合推荐算法

段琼; 虞慧群; 范贵生

doi:10.14135/j.cnki.1006-3080.20210303001

融合商品流行度与信任度的混合推荐算法

doi: 10.14135/j.cnki.1006-3080.20210303001

华东理工大学信息科学与工程学院，上海 200237

基金项目: 国家自然科学基金（61772200）；华东理工大学教育科研基金（ZH1726108）

详细信息

作者简介:
段琼：段　琼(1996-)，女，河南洛阳人，硕士生，主要研究方向为智能推荐算法。E-mail：754303271@qq.com

通讯作者:
虞慧群，E-mail：yhq@ecust.edu.cn

中图分类号: TP311
计量
- 文章访问数: 360
- HTML全文浏览量: 180
- PDF下载量: 39
- 被引次数: 0
出版历程
- 收稿日期: 2021-03-03
- 网络出版日期: 2021-06-16
- 刊出日期: 2022-08-26

A Hybrid Recommendation Algorithm Integrating Commodity Popularity and Trust

School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China

摘要

摘要: 目前协同过滤算法在推荐系统中的应用比较广泛，但由于数据的稀疏性，传统的协同过滤算法往往存在推荐准确性不高的问题。本文通过引入用户的社交信任网络挖掘用户的信任信息来缓解此问题。此外，考虑到热门项目在评分相似度计算时的贡献权重，在传统的评分相似计算公式中考虑了用户共同评分项占比带来的影响。在此基础上，提出了一种融合商品流行度与信任度的混合推荐算法（TPRA）。在Epinions数据集上的实验结果表明：该算法相较于对照算法在平均绝对误差（MAE）、均方根误差（RMSE）两个指标上至少降低了约3%。
- 信任网络 /
- 商品流行度 /
- 热门商品惩罚 /
- 数据稀疏
Abstract: At present, collaborative filtering algorithm has been widely used in the recommendation system, but due to the data sparsity problem, the traditional collaborative filtering algorithm often has the drawback of low recommendation accuracy. This paper alleviates this problem by introducing users’ social trust network to mine users’ trust information. Besides, considering the contribution weight of popular items in the calculation of scoring similarity, this paper combines the influence of the proportion of users’ common scoring items into the traditional scoring similarity calculation formula. On this basis, this paper proposes a hybrid recommendation model (TPRA) of integrating commodity popularity and trust. Finally, the experimental results on Epinions data set show that the proposed algorithm can achieve better results than the comparison algorithm, the proposed algorithm can reduce MAE and RMSE by at least about 3%.
- trust network /
- commodity popularity /
- hot goods punishment /
- data sparseness

HTML全文

图 1 TPRA算法框架图

Figure 1. Framework of TPRA algorithm

下载: 全尺寸图片幻灯片

图 2 用户U₁的社交网络图

Figure 2. Social network diagram of user U₁

下载: 全尺寸图片幻灯片

图 3 不同推荐算法的MAE(a)和RMSE(b)对比结果

Figure 3. MAE (a) and RMSE (b) comparison of different recommendation algorithms

下载: 全尺寸图片幻灯片

图 4 TPRA算法在不同子数据集下的指标对比

Figure 4. Indexes comparison of TPRA algorithm in different subdata sets

下载: 全尺寸图片幻灯片

表 1 TPRA模型参数设置

Table 1. Parameter setting of TPRA

d $\psi $ δ α

≤3 0.9 0.4 0.8

下载: 导出CSV

参考文献(15)

[1]	张岐山, 翁丽娟. 社会化推荐系统综述[J]. 计算机工程与应用, 2020, 56(1): 1-10. doi: 10.3778/j.issn.1002-8331.1907-0378
[2]	TIAN G, WANG Q, JIAN W, et al. Leveraging contextual information for cold-start Web service recommendation[J]. Concurrency and Computation Practice and Experience, 2019, 31(17): 1-17.
[3]	谢毅刚, 郭卫斌, 李建华. 基于双层相似度的协同过滤推荐算法[J]. 华东理工大学学报(自然科学版), 2018, 44(1): 131-138.
[4]	ZHAO W, ZHANG W. Collaborative filtering service recommendation algorithm based on trusted user and recommendation evaluation[C]//2018 IEEE 4th International Conference on Computer and Communications (ICCC). USA: IEEE, 2018: 2248-2255.
[5]	ZHU J, WANG C, GUO X, et al. Friend and POI recommendation based on social trust cluster in location-based social networks[J]. EURASIP Journal on Wireless Communications and Networking, 2019, 89(1): 1-12.
[6]	DUAN L, TIAN H, LIU K. A novel approach for Web service recommendation based on advanced trust relationships[J]. Information (Switzerland), 2019, 10(7): 233-246.
[7]	LI Y, LIU J, REN J, et al. A novel implicit trust recommendation approach for rating prediction[J]. IEEE Access, 2020, 8: 98305-98315. doi: 10.1109/ACCESS.2020.2997040
[8]	ZHOU Y, TANG Z, QI L, et al. Intelligent service recommendation for cold-start problems in edge computing[J]. IEEE Access, 2019, 7: 46637-46645. doi: 10.1109/ACCESS.2019.2909843
[9]	何利, 胡飘. 基于用户多维度信任的冷启动推荐模型[J]. 重庆邮电大学学报(自然科学版), 2018, 30(6): 827-834.
[10]	陈功平, 王红. 改进Pearson相关系数的个性化推荐算法[J]. 山东农业大学学报(自然科学版), 2016, 47(6): 940-944.
[11]	WANG D J, DENG S G, XU G D. Sequence-based context-aware music recommendation[J]. Information Retrieval Journal, 2018, 21: 230-252. doi: 10.1007/s10791-017-9317-7
[12]	CHEN J P, YING P G, ZOU M. Improving music recommendation by incorporating social influence[J]. Multimedia Tools and Applications, 2019, 78(3): 2667-2687. doi: 10.1007/s11042-018-5745-7
[13]	FU M, QU H, YI Z, et al. A novel deep learning-based collaborative filtering model for recommendation system[J]. IEEE Transactions on Cybernetics, 2018, 49(3): 1-13.
[14]	SINGH K, VERMA A K. A fuzzy-based trust model for flying ad hoc networks (FANETs)[J]. International Journal of Communication Systems, 2018, 31(6): 1-19.
[15]	MA G, WANG Y, ZHENG X, et al. A trust-aware latent space mapping approach for cross-domain recommendation[J]. Neurocomputing, 2020, 431(4): 100-110.