基于异构网络元路径的App推荐算法

›› 2020, Vol. 32 ›› Issue (4): 160-170.

基于异构网络元路径的App推荐算法

姜祎盼¹, 张文², 李健², 陈进东³

1. 北京化工大学经济管理学院, 北京 100029;
2. 北京工业大学经济管理学院, 北京 100124;
3. 北京信息科技大学经济管理学院, 北京 100192

收稿日期:2017-06-12 出版日期:2020-04-28 发布日期:2020-05-07
通讯作者: 张文(通讯作者),北京工业大学经济管理学院教授,博士生导师,博士
作者简介:姜祎盼,北京化工大学经济管理学院硕士研究生;李健,北京工业大学经济管理学院教授,博士生导师,博士;陈进东,北京信息科技大学经济管理学院副教授,硕士生导师,博士。
基金资助:
国家自然科学基金项目（71932002；71601023；61432001）；西安市科技计划创新基金项目（2016CXWL21）。

The App Recommendation Algorithm Based on Heterogeneous Network and Meta-path

Jiang Yipan¹, Zhang Wen², Li Jian², Chen Jindong³

1. School of Economics and Management, Beijing University of Chemical Technology, Beijing 100029;
2. School of Economics and Management, Beijing University of Technology, Beijing 100124;
3. School of Economics and Management, Beijing Information Science & Technology University, Beijing 100192

Received:2017-06-12 Online:2020-04-28 Published:2020-05-07

摘要/Abstract

摘要：

在当前形势下，移动终端用户获取自己感兴趣的移动应用App的一个重要渠道就是各种移动应用市场。从单个移动应用市场的角度来说，为保持自己对于用户的吸引力，它必须向用户推荐其可能感兴趣的移动应用App，以扩大自己在用户群体中的影响力和增加自己的被下载量。从个体用户的角度来说，面对移动应用市场上的大量操作和功能类似的移动应用App，他（她）必须克服选择困难从而高效地获取到让自己满意的移动应用App。为达成上述目的，本文提出了基于异构网络的移动用户App使用行为模型，并在此模型的基础之上提出了基于异构网络元路径的移动应用App推荐算法，以帮助移动应用市场快速感知其用户兴趣并根据用户兴趣快速获取移动应用App。基于移动应用App的用户使用标杆数据集，本文将所提出的算法与已有方法进行了一系列的对比试验。实验结果表明，基于异构网络元路径的App推荐算法显著改进了已有的移动应用App推荐方法。

关键词: App应用, 异构网络, 元路径, 推荐算法

Abstract:

With the rapid development of mobile Internet, users usually download Apps from mobile application markets. On the one hand, in order to expand the influence, individual mobile application market faces the situation of recommending App to users and keeping them. On the other hand, for a user, in the face of millions of Apps from every application market, how to choose the Apps that they really like is an urgent issue. This paper proposes a meta-path-based App recommendation approach based on heterogeneous network analysis. Using the real dataset from Talking Data, we verify the effectiveness of the proposed algorithm. We also compare the recommendation results of the meta-path-based recommendation algorithm and several baseline algorithms, including user-based collaborative filtering recommendation algorithm, item-based collaborative filtering recommendation algorithm and bipartite graph based recommendation algorithm. Experiment results show that meta-path-based algorithm produces better performances than the baseline algorithms on MAP and MRR measures.

Key words: App, heterogeneous network, recommendation algorithm, meta-path

姜祎盼, 张文, 李健, 陈进东. 基于异构网络元路径的App推荐算法[J]. , 2020, 32(4): 160-170.

Jiang Yipan, Zhang Wen, Li Jian, Chen Jindong. The App Recommendation Algorithm Based on Heterogeneous Network and Meta-path[J]. , 2020, 32(4): 160-170.

参考文献

[1] Adomavicius G., Tuzhilin A. Toward the Next Generation of Recommender Systems:A Survey of the State-of-the-Art and Possible Extensions[J]. IEEE Transactions on Knowledge & Data Engineering, 2005,17(6):734-749
[2] Balabanovi? M., Shoham Y. Fab:Content-based, Collaborative Recommendation[J]. Communication of the Acm, 1997,40(3):66-72
[3] Jeong B., Lee J., Cho H. An Iterative Semi-explicit Rating Method for Building Collaborative Recommender Systems[J]. Expert Systems with Applications, 2009,36(3):6181-6186
[4] 李涛. 推荐系统中若干关键问题研究[D]. 南京航空航天大学博士学位论文, 2009
[5] Resnick P., Iacovou N., Suchak M., et al. GroupLens:An Open Architecture for Collaborative Filtering of Netnews[C]. ACM Conference on Computer Supported Cooperative Work, ACM, 1994
[6] Sarwar B., Karypis G., Konstan J., et al. Item-based Collaborative Filtering Recommendation Algorithms[C]. International Conference on World Wide Web, ACM, 2001
[7] Burke R. Hybrid Recommender Systems:Survey and Experiments[C]. User Modeling and User-Adapted Interaction Volume, 2002
[8] Zhou T., Ren J., Medo M., et al. Bipartite Network Projection and Personal Recommendation[J]. Physical Review E Statistical Nonlinear & Soft Matter Physics, 2007,76(2):046115
[9] 冷亚军,陆青,张俊岭. 使用二分图网络提高协同推荐的准确性[J]. 计算机科学, 2015,42(3):256-260
[10] Karatzoglou A., Baltrunas L., Church K. Climbing the App Wall:Enabling Mobile App Discovery through Context-aware Recommendations[C]. CIKM'12:Proceedings of the ACM International Conference on Information and Knowledge Management, ACM, 2012
[11] Yin P., Luo P., Lee W. C., et al. App Recommendation:A Contest between Satisfaction and Temptation[C]. ACM International Conference on Web Search and Data Mining, ACM, 2013
[12] Lin J., Sugiyama K., Kan M. Y., et al. Addressing Cold-start in App Recommendation:Latent User Models Constructed from Twitter Followers[C]. International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, 2013
[13] Zhu H., Xiong H., Ge Y., et al. Mobile App Recommendations with Security and Privacy Awareness[C]. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014
[14] Liu B., Kong D., Cen L., et al. Personalized Mobile App Recommendation:Reconciling App Functionality and User Privacy Preference[C]. Eighth ACM International Conference on Web Search & Data Mining, ACM, 2015
[15] 程豪,吕晓玲,钟琰,等. 大数据背景下智能手机APP组合推荐研究[J]. 统计与信息论坛, 2016,31(6):86-91
[16] Ji M., Han J., Danilevsky M. Ranking-based Classification of Heterogeneous Information Networks[C]. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2011
[17] Zhang W., Wang S., Wang Q. KSAP:An Approach to Bug Report Assignment Using KNN Search and Heterogeneous Proximity[J]. Information & Software Technology, 2016,70:68-84
[18] 张文,姜祎盼,张思光,等. 基于经验分布和KL散度的协同过滤推荐质量评价研究[J]. 计算机应用研究, 2019,(9):1-10