Please wait a minute...
Data Analysis and Knowledge Discovery
Current Issue | Archive | Adv Search |
Research and Feature Analysis of Enterprise Microblog User Clustering Based on Supernetwork
Xi Yunjiang,Du Diedie,Liao Xiao,Zhang Xuehong
( School of Business Administration , South China University of Technology , Guangzhou 510641 , China)
(School of Internet Finance and Information Engineering , Guangdong University of Finance , Guangzhou 510521 , China)
Download: PDF(906 KB)  
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper proposes an integrated modeling method for multi-dimensional user interest data, and on this basis, studies the spectral clustering method of user interests.

[Methods] The paper takes the Weibo data of Three Squirrels as example.First,We use a supernetwork model to integrate the modeling of weibo content and user interaction data. Then, we construct an interactive interest index.Third, we combine the spectral clustering algorithm to divide the user groups.Finally, The clustering results are evaluated by the Silhouette Coefficient and Davies-Bouldin methods.

[Results] Comparing the optimal clustering effect of the three types of user feature vectors, it’s show that the clustering DB value of feature vectors based on topic interactive supernetworks is 0.57 when K is 15. Which is lower than feature vectors based on interactive data or blog content, with more even distribution among groups and tighter within groups.

[Limitations] More user characteristic data needs to be covered. In addition, the impact of different dimensions of data on user interests may be further explored.

[Conclusions] By analyzing the distribution and interest characteristics of enterprise microblog user groups, we propose corresponding maintenance and marketing suggestions, which will help companies better discover user interests and improve microblog marketing effect.

Key words supernetwork      enterprise microblog      user interests      spectral clustering      
Published: 21 May 2020
ZTFLH:  G206  
  F274  

Cite this article:

Xi Yunjiang, Du Diedie, Liao Xiao, Zhang Xuehong. Research and Feature Analysis of Enterprise Microblog User Clustering Based on Supernetwork . Data Analysis and Knowledge Discovery, 0, (): 1-.

URL:

http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech. 2096-3467.2020.0091     OR     http://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y0/V/I/1

[1] Lixin Xia,Jieyan Zeng,Chongwu Bi,Guanghui Ye. Identifying Hierarchy Evolution of User Interests with LDA Topic Model[J]. 数据分析与知识发现, 2019, 3(7): 1-13.
[2] Hui Nie. Modeling Users with Word Vector and Term-Graph Algorithm[J]. 数据分析与知识发现, 2019, 3(12): 30-40.
[3] Pengcheng Xu,Qiang Bi. Identifying Domain Experts Based on Knowledge Super-Network[J]. 数据分析与知识发现, 2019, 3(11): 89-98.
[4] Xiangdong Li,Fan Gao,Youhai Li. Categorizing Documents Automatically within Common Semantic Space[J]. 数据分析与知识发现, 2018, 2(9): 66-73.
[5] Jiang Wu,Chaocheng He,Panhao Ma. Analyzing Interaction of MOOC Users with Iteration Super Centrality[J]. 数据分析与知识发现, 2017, 1(8): 1-8.
[6] Jin Zeng,Wei Lu,Heng Ding,Haihua Chen. Modeling User’s Interests Based on Image Semantics[J]. 数据分析与知识发现, 2017, 1(4): 76-83.
[7] Meimei Chen, Kangjie Xue. Personalized Recommendation Algorithm Based on Modified Tensor Decomposition Model[J]. 数据分析与知识发现, 2017, 1(3): 38-45.
[8] Mengyao Xie,Xuwei Pan. Constructing Dynamic Social Tag Cloud for User Interests[J]. 数据分析与知识发现, 2017, 1(2): 35-40.
[9] Zhang Lei,Ma Jing,Li Dandan,Shen Yang. Hypernetwork Model for Semantic Social Network and Automatic Identification of Key Nodes[J]. 现代图书情报技术, 2016, 32(3): 8-17.
[10] Qiang Bi, Jian Liu, Yulai Bao. A New Text Clustering Method Based on Semantic Similarity[J]. 数据分析与知识发现, 2016, 32(12): 9-16.
[11] Gui Sisi, Lu Wei, Huang Shihao, Zhou Pengcheng. User Interest Prediction Combing Topic Model and Multi-time Function[J]. 现代图书情报技术, 2015, 31(9): 9-16.
[12] Liu Zhanbing, Xiao Shibin. Collaborative Filtering Recommended Algorithm Based on User's Interest Fuzzy Clustering[J]. 现代图书情报技术, 2015, 31(11): 12-17.
[13] Zhang Zhiwu. Sentiment Analysis of Product Reviews by means of Cross-domain Transfer Learning[J]. 现代图书情报技术, 2013, (6): 49-54.
[14] Zhao Pengwei, Ma Lin, Qin Chunxiu. Formation of Interest-based Peer-to-Peer Community[J]. 现代图书情报技术, 2013, 29(10): 53-58.
[15] Zhang Xing, Cai Shuqin, Xia Huosong, Hou Delin. Study on the Framework of an Enterprise's Knowledge Management System Based on Social Network[J]. 现代图书情报技术, 2011, 27(5): 36-41.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn