融合信任相似度的偏置概率矩阵分解算法

doi:10.6040/j.issn.1672-3961.0.2021.294

摘要/Abstract

摘要： 为解决社会化推荐算法推荐效果严重依赖用户信任数据的问题,提出一种融合信任相似度的偏置概率矩阵分解算法(bias probability matrix factorization algorithm fused with trust similarity, TTSPMF)。该算法引入稀疏性更低的信任相似度网络,使用信任关系的相似性弥补用户信任数据的稀疏性。通过用户信任矩阵计算得出信任相似度矩阵,然后将信任相似度矩阵和用户信任矩阵共同进行矩阵分解,同时加入偏置项来表达用户和物品的偏好,从而更好地刻画用户和物品的特征,避免因用户或物品本身因素带来的评分偏差。使用概率矩阵分解模型融合信任矩阵和信任相似度矩阵并迭代求解,得到用户特征矩阵和物品特征矩阵。在多个数据集上的试验证明,在不同评价指标下,该算法的推荐准确度明显高于传统推荐算法,可以有效缓解数据稀疏带来的推荐效果差的问题。

中图分类号:

TP301

王冰,马文明,武聪,郝昱猛. 融合信任相似度的偏置概率矩阵分解算法[J]. 山东大学学报 (工学版), 2022, 52(4): 110-117.

WANG Bing, MA Wenming, WU Cong, HAO Yumeng. Bias probability matrix factorization algorithm fused with trust similarity[J]. Journal of Shandong University(Engineering Science), 2022, 52(4): 110-117.

参考文献

[1] TAHMASBI H, JALALI M, SHAKERI H. Modeling user preference dynamics with coupled tensor factorization for social media recommendation[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 12(7):9693-9712.
[2] LI Y, LIOU J, LI Y. A social recommendation approach for reward-based crowdfunding campaigns[J]. Info-rmation & Management, 2020, 57(7):1-48.
[3] 张琦,柳玲,文俊浩.一种基于领域信任及不信任的奇异值分解推荐算法[J].计算机科学,2019,46(10):27-31. ZHANG Qi, LIU Ling, WEN Junhao. A singular value decomposition recommendation algorithm based on domain trust and distrust[J]. Computer Science, 2019, 46(10):27-31.
[4] YE M, DENG Y. Social recommendation combining trust relationship and distance metric factorization[J]. Journal of Circuits, Systems and Computers, 2020, 29(15):695-706.
[5] 崔春生,王辉,李群.基于用户标签和信任关系的协同过滤推荐算法研究[J].系统科学与数学,2019,39(3):437-448. CUI Chunsheng, WANG Hui, LI Qun. Research on collaborative filtering recommendation algorithm based on user tag and trust relationship[J]. System Science and Mathematics, 2019, 39(3):437-448.
[6] ZHANG X, CHEN X, SENG D, et al. A factored similarity model with trust and social influence for top-n recommendation[J]. International Journal of Computers Communications & Control, 2019, 14(4):590-607.
[7] POONGODI M, VIJAYAKUMAR V, RAWAL V, et al. Recommendation model based on trust relations & user credibility[J]. Journal of Intelligent & Fuzzy Systems, 2019, 36(2):1-8.
[8] 贾诗阳, 宾晟, 孙更新.融合多关系社交信任网络的推荐算法[J].信息与电脑(理论版), 2020, 32(13):40-41. JIA Shiyang, BIN Sheng, SUN Gengxin. A recommendation algorithm integrating mult-relationship social trust network [J]. Information and Computer(Theory Edition), 2020, 32(13):40-41.
[9] LI Y, HSIEH C, LIN L,et al. A social mechanism for task-oriented crowdsourcing recommendations[J]. Decision Support Systems, 2020, 141(1):1-16.
[10] 耿巧梦. 基于用户特征和信任度的推荐算法研究与实现[D]. 西安: 西安电子科技大学, 2019. GENG Qiaomeng. Research and implementation of recommendation algorithm based on user characteristics and trust[D]. Xi'an: Xidian University, 2019.
[11] 王瑞琴, 蒋云良, 李一啸, 等. 一种基于多元社交信任的协同过滤推荐算法[J].计算机研究与发展, 2016, 53(6):1389-1399. WANG Ruiqin, JIANG Yunliang, LI Yixiao,et al. A collaborative filtering recommendation algorithm based on multiple social trusts[J]. Computer Research and Development, 2016, 53(6):1389-1399.
[12] LIU Y, LIANG C, WU J, et al. A knowledge coverage-based trust propagation for recommendation mechanism in social network group decision making[J]. Applied Soft Computing Journal, 2021, 101(1):1-10.
[13] GUO L, LIANG J, ZHU Y, et al. Collaborative filtering recommendation based on trust and emotion[J]. Journal of Intelligent Information Systems, 2019, 53(1):113-135.
[14] 吴清春, 贾彩燕. 一种融合社交关系的矩阵分解推荐模型[J].计算机工程,2020,46(8):72-77. WU Qingchun, JIA Caiyan. A matrix factorization recommendation model integrating social relationships[J]. Computer Engineering, 2020, 46(8):72-77.
[15] ZHANG T, LI W, WANG L, et al. Social recommendation algorithm based on stochastic gradient matrix decom- position in social network[J]. Journal of Ambient Inteligence and Humanized Computing, 2020, 11(2):1-7.
[16] JAMALIM, ESTER M. A matrix factorization technique with trust propagation for recommendation in social networks[C] //Proceedings of the 4th ACM Conference on Recommender Systems. Barcelona, Spain: Association for Computing Machinery, 2010: 135-142.
[17] MA H, YANG H, LYU M, et al. SoRec:social recommendation using probabilistic matrix factorization[C] // Proceedings of the l7th ACM Conference on Information and Knowledge Management. Napa Valley, USA: Association for Computing Machinery, 2008: 931-940.
[18] 卫鼎峰,李梁,柴晶.融合物品信息的社会化推荐算法[J].计算机工程与应用,2021,57(19):198-204. WEI Dingfeng, LI Liang, CHAI Jing. Social recommend- ation algorithm fused with item information[J]. Computer Engineering and Applications, 2021, 57(19):198-204.
[19] WANG X, HE X, WANG M, et al. Neural graph collaborative filtering[C] //Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: Association for Computing Machinery, 2019: 165-174.
[20] 陈婷, 朱青, 周梦溪, 等.社交网络环境下基于信任的推荐算法[J].软件学报,2017,28(3):721-731. CHEN Ting, ZHU Qing, ZHOU Mengxi, et al. Trust-based recommendation algorithm in social network environment [J]. Journal of Software, 2017, 28(3):721-731.
[21] 逯泽馨. 社会化商务中融合用户信任和相似关系的推荐方法研究[D]. 大连:东北财经大学, 2019. LU Zexin. Research on recommendation method integrating user trust and similar relationships in social commerce[D]. Dalian: Dongbei University of Finance, 2019.
[22] SAJAD A, MAJID M, MOHSEN A. A social recommendation method based on an adaptive neighbor selection mechanism[J]. Information Processing and Management, 2018, 54(4):707-725.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed