基于用户相似性选择及标签距离的推荐算法

doi:10.3969/j.issn.0255-8297.2023.06.003

应用科学学报 ›› 2023, Vol. 41 ›› Issue (6): 940-957.doi: 10.3969/j.issn.0255-8297.2023.06.003

基于用户相似性选择及标签距离的推荐算法

苏湛, 陈学谦, 艾均, 黄忠

上海理工大学光电信息与计算机工程学院, 上海 200093

收稿日期:2022-05-24 出版日期:2023-11-30 发布日期:2023-11-30
通信作者: 苏湛,讲师,硕导,研究方向为智能控制、复杂网络、推荐系统。E-mail:suzhan@usst.edu.cn E-mail:suzhan@usst.edu.cn
基金资助:
国家自然科学基金(No.61803264)资助

Recommendation Algorithm Based on User Similarity Selection and Label Distance

SU Zhan, CHEN Xueqian, AI Jun, HUANG Zhong

School of Optical-Electronic and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2022-05-24 Online:2023-11-30 Published:2023-11-30

摘要/Abstract

摘要： 邻居选择和物品的标签信息对于推荐系统进行评分预测具有重要的影响。为了解决推荐系统中存在的预测和排序准确性低及算法可拓展性不足的问题。本文基于距离模型算法,提出了基于用户相似性选择及标签距离的推荐算法。首先,选取相似性大于阈值的用户作为待预测用户的邻居来应对算法可拓展性不足的问题。其次,利用物品的标签信息,将用户对物品的评分映射为用户对物品标签的评分以提高准确性。通过在两个电影数据集中利用十折验证预测用户对电影的评分。实验结果表明,基于用户相似性选择及标签距离的推荐算法在准确性以及可拓展性中均获得了较大提升。

关键词: 推荐系统, 协同过滤, 相似性筛选, 标签距离

Abstract: Neighbor selection and item label information have important influence on rating prediction of recommendation system. To improve the accuracy and scalability of recommendation systems, this paper proposes a distance-model based approach that utilizes user similarity selection and label distance. First, the users with similarity greater than the threshold value are selected as the neighbors of the users to be predicted to deal with insufficient scalability of the algorithm. Second, the user’s rating of the item is mapped to the user’s rating of the item label using the label information to enhance the accuracy. Users’ ratings of movies were predicted by using discount validation in both movie datasets. Experimental results show that the accuracy and scalability of the recommendation algorithm based on user similarity selection and label distance are greatly improved.

Key words: recommendation system, collaborative filtering, similarity screening, label distance

中图分类号:

P751.1

苏湛, 陈学谦, 艾均, 黄忠. 基于用户相似性选择及标签距离的推荐算法[J]. 应用科学学报, 2023, 41(6): 940-957.

SU Zhan, CHEN Xueqian, AI Jun, HUANG Zhong. Recommendation Algorithm Based on User Similarity Selection and Label Distance[J]. Journal of Applied Sciences, 2023, 41(6): 940-957.

参考文献

[1] JALiLi M, AhMADiAn S, IzADi M, et al. Evaluating collaborative filtering recommender algorithms:a survey[J]. IEEE Access, 2018, 6:74003-74024.
[2] 苏湛,王佳伟,艾均,等.相似性与置信系数为基础的推荐系统评分预测[J].小型微型计算机系统,2021, 42(5):984-989.Su Z, WAnG J W, Ai J, et al. Rating prediction in recommendation systems based on similarity and confidence coefficient[J]. Journal of Chinese Computer Systems, 2021, 42(5):984-989.(in Chinese)
[3] KATARTA R, VERMA O P. Recommender system with grey wolf optimizer and FCM[J]. Neural Computing and Applications, 2018, 30(5):1679-1687.
[4] AnAnD A, RAM M. System reliability management:solutions and technologies[M]. Boca Raton,Florida, USA:CRC Press, 2019:132-148.
[5] Li D S, LüQ, ShAnG L, et al. Efficient privacy-preserving content recommendation for online social communities[J]. Neurocomputing, 2017, 219:440-454.
[6] XionG R B, WAnG J, ZhAnG N, et al. Deep hybrid collaborative filtering for web service recommendation[J]. Expert Systems with Applications, 2018, 110:191-205.
[7] Hu R, Dou W C, Liu J X. ClubCF:a clustering-based collaborative filtering approach for big data application[J]. IEEE Transactions on Emerging Topics in Computing, 2014, 2(3):302-313.
[8] 苏湛,林祖夷,艾均.类型相似性与品味影响力的推荐系统评分预测[J].小型微型计算机系统, 2021,42(12):2530-2537.Su Z, Lin Z Y, Ai J. Rating prediction in recommender systems based on type similarity and taste influence[J]. Journal of Chinese Computer Systems, 2021, 42(12):2530-2537.(in Chinese)
[9] Ro BiLLARD M, WALkER R, ZiMMERMAnn T. Recommendation systems for software engineering[J]. IEEE Software, 2010, 27(4):80-86.
[10] Guo T L, Luo J Z, DonG K, et al. Locally differentially private item-based collaborative filtering[J]. Information Sciences, 2019, 502:229-246.
[11] Li N, Li C P. Accumulative influence weight collaborative filtering recommendation approach[M]//Opportunities and Challenges for Next-Generation Applied Intelligence. Berlin, Heidelberg:Springer, 2009:73-78.
[12] Ai J, CAi Y F, Su Z, et al. Predicting user-item links in recommender systems based on similarity-network resource allocation[J]. Chaos, Solitons&Fractals, 2022, 158:112032.
[13] Li K K, Zhou X Z, Lin F, et al. Deep probabilistic matrix factorization framework for online collaborative filtering[J]. IEEE Access, 2019, 7:56117-56128.
[14] LAnGsETh H, NiELsEn T D. A latent model for collaborative filtering[J]. International Journal of Approximate Reasoning, 2012, 53(4):447-466.
[15] LEMiRE D, MAcLAchLAn A. Slope one predictors for online rating-based collaborative filtering[C]//2005 SIAM International Conference on Data Mining, 2005:471-475.
[16] 马鑫,吴云,鹿泽光.基于混合神经网络的协同过滤推荐模型[J].应用科学学报, 2020, 38(3):478-487.MA X, Wu Y, Lu Z G. Collaborative filtering recommendation model based on hybrid neural network[J]. Journal of Applied Sciences, 2020, 38(3):478-487.(in Chinese)
[17] BATMAz Z, YuREkLi A, BiLGE A, et al. A review on deep learning for recommender systems:challenges and remedies[J]. Artificial Intelligence Review, 2019, 52(1):1-37.
[18] Joy J, PiLLAi R V G. Review and classification of content recommenders in E-learning environment[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(9):7670-7685.
[19] Mu R H. A survey of recommender systems based on deep learning[J]. IEEE Access, 2018, 6:69009-69022.
[20] WiLLMoTT C J, MATsuuRA K. Advantages of the mean absolute error(MAE)over the root mean square error(RMSE)in assessing average model performance[J]. Climate Research, 2005,30:79-82.
[21] HE X S, Zhou M Y, Zhuo Z, et al. Predicting online ratings based on the opinion spreading process[J]. Physica A:Statistical Mechanics and Its Applications, 2015, 436:658-664.
[22] JAvARi A, GhARiBshAh J, JALiLi M. Recommender systems based on collaborative filtering and resource allocation[J]. Social Network Analysis and Mining, 2014, 4(1):234.
[23] Ai J, Liu Y Y, Su Z, et al. Link prediction in recommender systems based on multi-factor network modeling and community detection[J]. EPL(Europhysics Letters), 2019, 126(3):38003.
[24] SinGh P K, SinhA M, DAs S, et al. Enhancing recommendation accuracy of item-based collaborative filtering using Bhattacharyya coefficient and most similar item[J]. Applied Intelligence,2020, 50(12):4708-4731.
[25] LEE S. Using entropy for similarity measures in collaborative filtering[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 11(1):363-374.
[26] Su Z, Lin Z Y, Ai J, et al. Rating prediction in recommender systems based on user behavior probability and complex network modeling[J]. IEEE Access, 2021, 9:30739-30749.
[27] KLuvER D, EksTRAnD M D, KonsTAn J A. Rating-based collaborative filtering:algorithms and Evaluation[M]//Social Information Access. Cham:Springer, 2018:344-390.
[28] WAnG Y, WAnG L, Li Y, et al. A theoretical analysis of NDCG ranking measures[C]//26th Annual Conference on Learning Theory, 2013, 8:6.

基于用户相似性选择及标签距离的推荐算法

Recommendation Algorithm Based on User Similarity Selection and Label Distance

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	季德强, 王海荣, 车淼, 王嘉鑫. KNN-GWD推荐模型及其应用[J]. 应用科学学报, 2022, 40(1): 145-154.
[2]	贾丹, 孙静宇. 基于用户会话的TF-Ranking推荐方法[J]. 应用科学学报, 2021, 39(3): 495-494.
[3]	马鑫, 吴云, 鹿泽光. 基于混合神经网络的协同过滤推荐模型[J]. 应用科学学报, 2020, 38(3): 478-487.
[4]	朱文强, 钟元生. 基于声誉计算的可信O2O服务提供商推荐方法[J]. 应用科学学报, 2017, 35(5): 585-601.
[5]	程树林, 张博锋, 邹国兵. 基于用户和项目的双视角协同过滤推荐方法[J]. 应用科学学报, 2017, 35(3): 326-336.
[6]	黄东晋，唐鹏斌，王音，丁友东. 基于交互历史的三维家居个性化推荐与虚拟展示[J]. 应用科学学报, 2015, 33(4): 407-418.