计算机科学 ›› 2021, Vol. 48 ›› Issue (7): 124-129.doi: 10.11896/jsjkx.200600096

• 数据库&大数据&数据科学 • 上一篇    下一篇

融入结构度中心性的社交网络用户影响力评估算法

谭琪, 张凤荔, 王婷, 王瑞锦, 周世杰   

  1. 电子科技大学信息与软件工程学院(软件工程) 成都610054
  • 收稿日期:2020-06-16 修回日期:2020-12-04 出版日期:2021-07-15 发布日期:2021-07-02
  • 通讯作者: 张凤荔(fzhang@uestc.edu.cn)
  • 基金资助:
    国家自然科学基金(61802033,61472064,61602096);四川省区域创新合作项目(2020YFQ0018);四川省科技计划(2018GZ0087,2019YJ0543);博士后基金项目(2018M643453);广东省国家重点实验室项目(2017B030314131);网络与数据安全四川省重点实验室开放课题(NDSMS201606)

Social Network User Influence Evaluation Algorithm Integrating Structure Centrality

TAN Qi, ZHANG Feng-li, WANG Ting, WANG Rui-jin, ZHOU Shi-jie   

  1. School of Information and Software Engineering(Software Engineering),University of Electronic Science and Technology of China,Chengdu 610054,China
  • Received:2020-06-16 Revised:2020-12-04 Online:2021-07-15 Published:2021-07-02
  • About author:TAN Qi,born in 1996,postgraduate,is a member of China Computer Federation.Her main research interests include machine learning,data mining and cascading forecasting.(tanqi1012more@163.com)
    ZHANG Feng-li,born in 1963,Ph.D,professor,doctoral supervisor,is a member of China Computer Federation.Her main research interests include network security and network engineering,cloud computing and big data,and machine learning.
  • Supported by:
    National Natural Science Foundation of China(61802033,61472064,61602096),Sichuan Regional Innovation Cooperation Project(2020YFQ0018),Science and Technology Project of Sichuan Province(2018GZ0087,2019YJ0543),Postdoctoral Fund Project(2018M643453),State Key Laboratory Project of Guangdong Province(2017B030314131) and Network and Data Security Key Laboratory of Sichuan Province(NDSMS201606).

摘要: 在社交网络中,通过追踪极少数的强影响力用户,可以实现宏观管控信息的传播过程,而用户影响力是一种无法预判的后验信息,仅能依靠有关特征来确定。因此,提出了一种融入结构度中心性的社交网络用户影响力评估(Structural-Degree-Centrality User Influence Rank,SDRank)算法来识别强影响力用户。该算法基于PageRank算法,引入了结构度中心性,结合了加入时间与平均转发数的调节因子,进而计算出用户的影响力值。相较于其他的现有算法,SDRank算法仅从用户本身的行为角度出发,不需要诸如个人标签、粉丝等存在伪造风险与缺省可能的具体信息,也不必挖掘传播内容的潜在信息,适用性更广泛。以微博用户的级联转发数据集作为实验对象,对被转发数排名Top-K用户的平均转发数等相关结果进行了可视化分析,探讨了用户转发行为在社交网络信息传播中的作用。在实验过程中,所提算法与PageRank,TrustRank算法相比,准确率、召回率和F1-measure值都有了一定的提高,验证了SDRank算法的有效性。

关键词: 度中心性, 社交网络, 用户行为, 用户影响力

Abstract: In social networks,the transmission process of information can be controlled macro by tracking a small number of strongly influential users,but user influence is a kind of posterior information that cannot be predicted and can only be determined by relevant characteristics.Therefore,this paper proposes a social network user influence evaluation algorithm that integrates structural degree centrality to identify users with strong influence.As an evaluation algorithm for social network user influence,SDRank is developed based on an improved PageRank algorithm,which introduces structural degree centrality,combines the re-gulatory factor of join time and average forward number,and then calculates the user’s influence.Compared to other existing algorithms,SDRank is applicable to a broader set of scenarios from a user behavior perspective,for it doesn’t require specific information(such as personal tags,fans) that have potential forgery risks or default possibilities,and doesn’t have to exploit the under-lying information of disseminated content.This paper takes the cascade forwarding dataset of Weibo users as the experimental object,makes a visual analysis of the average forwarding number of top-K users and other relevant results,and discusses the role of user forwarding behavior in information transmission in social network.During the experiment,its accuracy,recall rate and F1-measure value are greatly improved compared with PageRank and TrustRank,and the effectiveness of SDRank algorithm is verified.

Key words: Degree centrality, Social network, User behavior, User influence

中图分类号: 

  • TP391
[1]ILIE V,TUREL O.Manipulating user resistance to large-scale information systems through influence tactics[J].Information &Management,2019,57(3):103178.
[2]ZAREIE A,SHEIKHAHMADI A,JALILI M.Identification of influential users in social networks based on users’ interest[J].Information Sciences,2019,493:217-231.
[3]HUANG X Y,YANG A Z,LIU X Y,et al.An Improved In-fluence assessment algorithm for Weibo users[J].Computer Engineering,2019,45(12):294-299.
[4]JU C H,ZHAO K D,BAO F G.Influence Strength Calculation Model of Social Network Users integrating Closeness Centrality and Credit[J].Chinese Journal of Intelligence,2019,38(2):170-177.
[5]CHENG S,JIANG C,REN K.The Influence of the Central Path Media Blog Post Information Characteristics on User Behavior[C]//Institute of Management Science and Industrial Enginee-ring:Computer Science and Electronic Technology International Society.2019:8.
[6]WEI J M,HE H.Research on user Behavior and Influence Assessment Algorithm in Social Network[J].Intelligent Computer and Application,2019,9(2):162-167.
[7]ZHANG C,TANG K,PENG Y B.Fuzzy Comprehensive Evalua-tion of social Network Users’ Influence[J].Computer System Application,2017,26(12):18-24.
[8]WANG Z F,ZHU J Y,ZHENG Z Y,et al.Influence analysis of Users in Weibo Community based on RC Model[J].Computer Science,2017,44(3):254-258,282.
[9]XING Y F,WANG X W,HAN X W,et al.Research on in-fluence of network nodes in new media environment based on information entropy-case study of WeChat public account[J].Books and Intelligence Work,2018,62(5):76-86.
[10]ZHANG J D,YANG Y.Research on influence MeasurementModel of Mobile Social Network Users based on interactive behavior and emotional tendency[J].Intelligence Theory and Practice,2019,42(1):112.
[11]HAN Z M,MAO R,ZHENG C Y,et al.An effective dynamic network Node influence model[J].Computer Application Research,2019(7):1960-1964.
[12]PAGE L,BRIN S,MOTWANI R,et al.The pagerank citation ranking:Bringing order to the web[R].Stanford InfoLab,1999.
[13]KWAK H,LEE C,PARK H,et al.What Is Twitter,a SocialNetwork or a News Media?[C]//Proceedings of the 19th International Conference on World Wide Web.2010.
[14]SU S Q,YANG K,ZHANG N.Comparative Study of Leader-Rank and PageRank Algorithms[J].Information Technology,2015(4):8-11.
[15]WEI J D,QIN X Z,JIA Z H,et al.User Influence Evaluation Model based on user behavior and Structural hole[J].Modern Electronic Technology,2019(5):39.
[16]WANG J,YU W,HU Y H,et al.Social Network InfluenceMaximization Algorithm based on 3-Layer Centrality[J].Computer Science,2014,41(1):59-63.
[17]CHEN X L.Research on Social Network Influence Maximization Algorithm and Its Propagation Model[D].Harbin:Harbin Engineering University,2016:20-22.
[18]YANG S X,LIANG W,ZHU K L.Influence measurementmethod of nodes in complex network based on three-level neighbors [J].Journal of Electronics and Information Technology,2020,42.
[19]BACHA R E,ZIN T T.A Survey on Influence and Information Diffusion in Twitter Using Big Data Analytics[C]//Internatio-nal Conference on Big Data Analysis and Deep Learning Applications.Singapore:Springer,2018:39-47.
[20]YU J.Empirical Analysis on the Characteristics of Users’ in-fluence in the Process of Microblog communication [J].Journal of Intelligence,2013(8):61-65.
[21]LOU S,ZHOU M,QU Q.Analysis of User Influence of Social Investment Platform-Taking Snowball Network as an Example[J].Service Science and Mangement,2019,8(6):251-262.
[22]CAO Q,SHEN H W,CEN K T,et al.DeepHawkes:Bridgingthe Gap between Prediction and Understanding of Information Cascades[C]//CIKM 2017.2017:1149-1158.
[23]ZHANG N,RAO J,ZHANG S Q,et al.Power-law distribution phenomenon of sina weibo forwarding number[J].Computer Age,2015(3):33-35.
[24]GYONGYI Z,GARCIAMOLINA H,PEDERSEN J.Combating web spam with trustrank[C]//Proceedings of the 2004 International Conference on Very Large Data Bases (VLDB).Toronto,2004:576-587.
[25]ZHAO J Q,GUI X L,TIAN F.A New Method of Identifying Influential Users in the Micro-Blog Networks[J].IEEE Access,2017,5:3008-3015.
[1] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[2] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[3] 魏鹏, 马玉亮, 袁野, 吴安彪.
用户行为驱动的时序影响力最大化问题研究
Study on Temporal Influence Maximization Driven by User Behavior
计算机科学, 2022, 49(6): 119-126. https://doi.org/10.11896/jsjkx.210700145
[4] 余皑欣, 冯秀芳, 孙静宇.
结合物品相似性的社交信任推荐算法
Social Trust Recommendation Algorithm Combining Item Similarity
计算机科学, 2022, 49(5): 144-151. https://doi.org/10.11896/jsjkx.210300217
[5] 畅雅雯, 杨波, 高玥琳, 黄靖云.
基于SEIR的微信公众号信息传播建模与分析
Modeling and Analysis of WeChat Official Account Information Dissemination Based on SEIR
计算机科学, 2022, 49(4): 56-66. https://doi.org/10.11896/jsjkx.210900169
[6] 左园林, 龚月姣, 陈伟能.
成本受限条件下的社交网络影响最大化方法
Budget-aware Influence Maximization in Social Networks
计算机科学, 2022, 49(4): 100-109. https://doi.org/10.11896/jsjkx.210300228
[7] 郭磊, 马廷淮.
基于好友亲密度的用户匹配
Friend Closeness Based User Matching
计算机科学, 2022, 49(3): 113-120. https://doi.org/10.11896/jsjkx.210200137
[8] 王剑, 王玉翠, 黄梦杰.
社交网络中的虚假信息:定义、检测及控制
False Information in Social Networks:Definition,Detection and Control
计算机科学, 2021, 48(8): 263-277. https://doi.org/10.11896/jsjkx.210300053
[9] 张人之, 朱焱.
基于主动学习的社交网络恶意用户检测方法
Malicious User Detection Method for Social Network Based on Active Learning
计算机科学, 2021, 48(6): 332-337. https://doi.org/10.11896/jsjkx.200700151
[10] 鲍志强, 陈卫东.
基于最大后验估计的谣言源定位器
Rumor Source Detection in Social Networks via Maximum-a-Posteriori Estimation
计算机科学, 2021, 48(4): 243-248. https://doi.org/10.11896/jsjkx.200400053
[11] 张少杰, 鹿旭东, 郭伟, 王世鹏, 何伟.
供需匹配中的非诚信行为预防
Prevention of Dishonest Behavior in Supply-Demand Matching
计算机科学, 2021, 48(4): 303-308. https://doi.org/10.11896/jsjkx.200900090
[12] 袁得嵛, 陈世聪, 高见, 王小娟.
基于斯塔克尔伯格博弈的在线社交网络扭曲信息干预算法
Intervention Algorithm for Distorted Information in Online Social Networks Based on Stackelberg Game
计算机科学, 2021, 48(3): 313-319. https://doi.org/10.11896/jsjkx.200400079
[13] 谭琪, 张凤荔, 张志扬, 陈学勤.
社交网络用户影响力的建模方法
Modeling Methods of Social Network User Influence
计算机科学, 2021, 48(2): 76-86. https://doi.org/10.11896/jsjkx.191200102
[14] 郁友琴, 李弼程.
基于多粒度文本特征表示的微博用户兴趣识别
Microblog User Interest Recognition Based on Multi-granularity Text Feature Representation
计算机科学, 2021, 48(12): 219-225. https://doi.org/10.11896/jsjkx.201100128
[15] 马理博, 秦小麟.
话题-位置-类别感知的兴趣点推荐
Topic-Location-Category Aware Point-of-interest Recommendation
计算机科学, 2020, 47(9): 81-87. https://doi.org/10.11896/jsjkx.191100120
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!