计算机应用 ›› 2020, Vol. 40 ›› Issue (9): 2606-2612.DOI: 10.11772/j.issn.1001-9081.2020010095

• 数据科学与技术 • 上一篇    下一篇

基于模块度和标签传递的推荐算法

盛俊1,2, 李斌1, 陈崚1   

  1. 1. 扬州大学 信息工程学院, 江苏 扬州 225000;
    2. 扬州市职业大学 信息工程学院, 江苏 扬州 225000
  • 收稿日期:2020-02-07 修回日期:2020-04-20 出版日期:2020-09-10 发布日期:2020-04-28
  • 通讯作者: 盛俊
  • 作者简介:盛俊(1972-),男,江苏扬州人,副教授,硕士,CCF会员,主要研究方向:数据挖掘、复杂网络分析;李斌(1965-),男,江苏扬州人,教授,博士生导师,博士,CCF会员,主要研究方向:人工智能、知识工程;陈崚(1951-),男,江苏扬州人,教授,博士生导师,CCF会员,主要研究方向:数据挖掘、并行与分布式处理、复杂网络分析。
  • 基金资助:
    国家自然科学基金资助项目(61379066,61472344,61402395);江苏省自然科学基金资助项目(BK20140492);江苏省教育厅自然科学基金资助项目(13KJB520026);江苏省六大人才高峰项目(2011-DZXX-032);江苏省高等职业院校专业带头人高端研修项目(2019GRFX115);扬州市职业大学校级重点科研项目(2018ZR04)。

Recommendation algorithm based on modularity and label propagation

SHENG Jun1,2, LI Bin1, CHEN Ling1   

  1. 1. School of Information Engineering, Yangzhou University, Yangzhou Jiangsu 225000, China;
    2. School of Information Engineering, Yangzhou Polytechnic College, Yangzhou Jiangsu 225000, China
  • Received:2020-02-07 Revised:2020-04-20 Online:2020-09-10 Published:2020-04-28
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61379066, 61472344, 61402395), the Natural Science Foundation of Jiangsu Province(BK20140492), the Natural Science Fund of Jiangsu Provincial Department of Education (13KJB520026), the Six Talent Peaks Project in Jiangsu Province (2011-DZXX-032), the Jiangsu Higher Vocational College Professional Leader High-End Training Project (2019GRFX115), the Key Scientific Research Project of Yangzhou Polytechnic College (2018ZR04).

摘要: 针对基于网络信息的商品推荐的问题,提出了在二部网络上基于社区挖掘和标签传递的推荐算法。首先,用带权的二部图来表达用户-项目的评分矩阵,利用标签传递技术对二部网络进行社区挖掘;然后,基于二部网络中的社区结构信息,充分利用用户所在的社区之间的相似性以及项目之间、用户之间的相似性来挖掘用户可能感兴趣的项目;最后,向用户进行项目的推荐。在实际网络上的实验结果表明,与基于双向关联规则项目评分预测的推荐算法(BAR-CF)、基于项目评分预测的推荐算法(IR-CF)、基于网络链接预测的用户偏好预测方法(PLP)和改进的基于用户的协同过滤的方法(MU-CF)相比,该算法的平均绝对差(MAE)低0.1~0.3,准确率高0.2。因此,所提算法可以取得比其他类似方法更高质量的推荐结果。

关键词: 社交网络, 推荐, 二部图, 社区挖掘, 模块度标签传递

Abstract: To solve the problem of commodity recommendation based on network information, a recommendation algorithm based on community mining and label propagation on bipartite network was proposed. Firstly, a weighted bipartite graph was used to represent the user-item scoring matrix, and the label propagation technology was adopted to perform the community mining to the bipartite network. Then, the items which the users might be interested in were mined based on the community structure information of the bipartite network and by making full use of the similarity between the communities that the users in as well as the similarity between items and the similarity between the users. Finally, the item recommendation was performed to the users. The experimental results on real world networks show that, compared with the Collaborative Filtering recommendation algorithm based on item rating prediction using Bidirectional Association Rules (BAR-CF), the Collaborative Filtering recommendation algorithm based on Item Rating prediction (IR-CF), user Preferences prediction method based on network Link Prediction (PLP) and Modified User-based Collaborative Filtering (MU-CF), the proposed algorithm has the Mean Absolute Error (MAE) 0.1 to 0.3 lower, and the precision 0.2 higher. Therefore, the proposed algorithm can obtain recommendation results with higher quality compared to other similar methods.

Key words: social network, recommendation, bipartite graph, community mining, modularity label propagation

中图分类号: