Multi-granularity User Portrait Based on Granular Computing
JIANG Minghui1,2, MIAO Duoqian1,2, LUO Sheng1,2, ZHAO Cairong1,2
1.Department of Computer Science and Technology, Tongji University, Shanghai 201804
2.Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai 201804
Single model with single granularity is employed to process multi-sources heterogeneous raw data in the existing user portrait models. The performance of the analytic model is limited and the multi-level and multi-angle user portrait features cannot be fully displayed. Aiming at this problem, based on the idea of granular computing, a multi-granularity user portrait model is proposed. Firstly, a multi-granular representation structure of the data is constructed to granulate the raw data. Then, according to the data granularity structure, a granularity upgrade algorithm based on ensemble learning is proposed. Low-level data information is fused to obtain high-level data representation. Finally, user portrait analysis is carried out at multi-level data representation to show a more comprehensive portrait. Experiments show that the user portrait with multiple granularities is more comprehensive, stereoscopic and richer than the single granularity user portrait.
[1] GU H Q, WANG J, WANG Z W, et al. Modeling of User Portrait through Social Media // Proc of the IEEE International Conference on Multimedia and Expo. Washington, USA: IEEE, 2018. DOI: 10.1109/ICME.2018.8486595.
[2] 陈慧香,邵 波.国外图书馆领域用户画像的研究现状及启示.图书馆学研究, 2017(20): 16-20.
(CHEN H X, SHAO B. The Research Status and Enlightenment of the User Profile in the Library Fields at Abroad. Research on Library Science, 2017(20): 16-20.)
[3] GAUCH S, SPERETTA M, CHANDRAMOULI A, et al. User Profiles for Personalized Information Access // BRUSILOVSKY D, KOBSA A, NEJDL W, eds. The Adaptive Web, Methods and Stra-tegies of Web Personalization. Berlin, Germany: Springer, 2007: 54-89.
[4] TEIXEIRA C, PINTO J S, MARTINS J A. User Profiles in Organizational Environments. Campus-Wide Information Systems, 2008, 25(3): 128-144.
[5] BILLSUS D, PAZZANO M J. A Hybrid User Model for News Story Classification // Proc of the 7th International Conference on User Modeling. Berlin, Germany: Springer, 1999: 99-108.
[6] LAINÉ-CRUZEL S, LAFOUGE T, LARDY J P, et al. Improving Information Retrieval by Combining User Profile and Document Segmentation. Information Processing and Management, 1996, 32(3): 305-315.
[7] 李映坤.大数据背景下用户画像的统计方法实践研究.硕士学位论文.北京:首都经济贸易大学, 2016.
(LI Y K. Practical Research on Statistical Methods of User Portraits in the Background of Big Data. Master Dissertation. Beijing, China: Capital University of Economics and Business, 2016.)
[8] 张小可,沈文明,杜翠凤.贝叶斯网络在用户画像构建中的研究.移动通信, 2016, 40(22): 22-26.
(ZHANG X K, SHEN W M, DU C F. Research on Bayesian Network in User Portrait Construction. Mobile Communications, 2016, 40(22): 22-26.)
[9] 张 哲.基于微博数据的用户画像系统的设计与实现.硕士学位论文.武汉:华中科技大学, 2015.
(ZHANG Z. Design and Implementation of User Portrait System Based on Microblog Data. Master Dissertation. Wuhan, China: Huazhong University of Science and Technology, 2015.)
[10] 刘 速.浅议数字图书馆知识发现系统中的用户画像——以天津图书馆为例.图书馆理论与实践, 2017(6): 103-106.
(LIU S. The Persona in Digital Library Knowledge Discovery System-Taking Tianjin Library as an Example. Library Theory and Practice, 2017(6): 103-106.)
[11] 高玉龙.基于文本挖掘的用户画像研究.硕士学位论文.汕头:汕头大学, 2014.
(GAO Y L. Users Portrait Research Based on Text Mining. Master Dissertation. Shantou, China: Shantou University, 2014.)
[12] 李 冰,王 悦,刘永祥.大数据环境下基于K-means的用户画像与智能推荐的应用.现代计算机, 2016(24): 11-15.
(LI B, WANG Y, LIU Y X. Application of User Portrait and Intelligent Recommendation Based on Big Data Technology and K-means. Modern Computer, 2016(24): 11-15.)
[13] SUGIYAMA K, HATANO K, YOSHIKAWA M. Adaptive Web Search Based on User Profile Constructed without any Effort from Users[C/OL]. [2019-05-25]. https://www.iw3c2.org/WWW2004/docs/1p675.pdf.
[14] ZHAO C R, WANG X K, MIAO D Q, et al. Maximal Granularity Structure and Generalized Multi-view Discriminant Analysis for Person Re-identification. Pattern Recognition, 2018, 79: 79-96.
[15] YAO Y Y. Interpreting Concept Learning in Cognitive Informatics and Granular Computing. IEEE Transactions on Systems, Man, and Cybernetics(Cybernetics), 2009, 39(4): 855-866.
[16] LAU J H, BALDWIN T. An Empirical Evaluation of Doc2Vec with Practical Insights into Document Embedding Generation // Proc of the 1st Workshop on Representation Learning for NLP. Stroudsburg, USA: ACL, 2016: 78-86.
[17] RAMOS J. Using TF-IDF to Determine Word Relevance in Document Queries // Proc of the 1st Instructional Conference on Machine Learning. Berlin, Germany: Springer, 2003. DOI: 10.15804/tner.2015.42.4.03.
2019, Vol. 32 
