您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

《山东大学学报(理学版)》 ›› 2019, Vol. 54 ›› Issue (9): 105-113.doi: 10.6040/j.issn.1671-9352.1.2018.115

• • 上一篇    下一篇

基于多元信息融合的用户关联模型

杨亚茹*,王永庆,张志斌,刘悦,程学旗   

  1. 中国科学院计算技术研究所, 北京 100190
  • 出版日期:2019-09-20 发布日期:2019-07-30
  • 作者简介:杨亚茹(1993— ),女,硕士,工程师,研究方向为社会计算. E-mail:yangyaru@ict.ac.cn*通信作者
  • 基金资助:
    国家重点基础研究发展计划资助项目(2014CB340401);国家自然科学基金资助项目(61802371,61472400,91746301)

Social network user identity linkage model based on comprehensive information

YANG Ya-ru*, WANG Yong-qing, ZHANG Zhi-bin, LIU Yue, CHENG Xue-qi   

  1. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Online:2019-09-20 Published:2019-07-30

摘要: 随着社交媒体网站的日益普及,用户倾向于加入多个社交网络,作为社交媒体中的一项新兴工作,将社交网络的多个用户身份关联起来具有重要意义。通过研究目前有代表性的用户关联模型,提出了一个基于综合信息的用户关联模型(BiALP),该模型通过节点表达的方法学习网络的内在结构信息、属性信息和内容信息,以源网络和目标网络的节点表达为特征,以已关联用户对作为带标签数据,采用二分类监督学习的方式学习源网络与目标网络之间的关联关系。大量实验表明,BiALP模型与目前有代表性的其他用户关联模型相比效果有明显的提升(35%),能够实现更精确的用户关联。

关键词: 用户关联, 网络表达, 监督学习

Abstract: With the increasing popularity of social media sites, users prefer to join multiple online social networks, how to associate multiple user identities in a social network as a new job in social media is of great significance. This paper studies a representative user identity linkage model and proposes a user identity linkage model based on comprehensive information(BiALP). The model learns the internal structure information, attribute information and content information of the network through the node expression method. It is characterized by the node representation of the source network and the target network, and is based on the associated user pairs. With tagged data, the relationship between the source network and the target network is learned through a binary supervised learning manner. A large number of experiments have shown that the BiALP model has a significant improvement(35%)compared to other representative user identity linkage models.

Key words: user linkage, network embedding, supervised learning

中图分类号: 

  • TP391
[1] MANIKONDA L, MEDURI V V, KAMBHAMPATI S. Tweeting the mind and instagramming the heart: exploring differentiated content sharing on social media[C] //Tenth International AAAI Conference on Web and Social Media. Cologne: AAAI Press, 2016: 639-642.
[2] CARMAGNOLA F, CENA F. User identification for cross-system personalisation[J]. Information Sciences, 2009, 179(1/2):16-32.
[3] DENG Z, SANG J, XU C. Personalized video recommendation based on cross-platform user modeling[C] // 2013 IEEE International Conference on Multimedia and Expo(ICME). San Jose: IEEE, 2013: 1-6.
[4] YAN M, SANG J, MEI T, et al. Friend transfer: cold-start friend recommendation with cross-platform transfer learning of social knowledge[C] // 2013 IEEE International Conference on Multimedia and Expo(ICME). San Jose: IEEE, 2013: 1-6.
[5] KUMAR S, ZAFARANI R, LIU H. Understanding user migration patterns in social media[C] // AAAI. San Francisco: AI Access Foundation, 2011, 11:8-11.
[6] SHU K, WANG S H, TANG J L, et al. User identity linkage across online social networks[J]. ACM SIGKDD Explorations Newsletter, 2017, 18(2):5-17.
[7] ZAFARANI R, LIU H. Connecting users across social media sites: a behavioral-modeling approach[C] // Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago: ACM, 2013: 41-49.
[8] MAN T, SHEN H, LIU S, et al. Predict anchor links across social networks via an embedding approach[C] // IJCAI. New York: International Joint Conferences on Artificial Intelligence, 2016, 16:1823-1829.
[9] LIU S, WANG S, ZHU F, et al. Hydra: large-scale social identity linkage via heterogeneous behavior modeling[C] // Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data. Snowbird: ACM, 2014: 51-62.
[10] RONG X. word2vec parameter learning explained[J]. arXiv preprint arXiv:1411.2738, 2014.
[11] KLEMA V, LAUB A. The singular value decomposition: its computation and some applications[J]. IEEE Transactions on Automatic Control, 1980, 25(2):164-176.
[12] CUI Y, PEI J, TANG G T, et al. Finding email correspondents in online social networks[J]. World Wide Web, 2013, 16(2):195-218.
[13] TANG J, QU M, WANG M, et al. Line: large-scale information network embedding[C] // Proceedings of the 24th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee. Florence: Association for Computing Machinery, 2015: 1067-1077.
[14] RUCK D W, ROGERS S K, KABRISKY M, et al. The multilayer perceptron as an approximation to a Bayes optimal discriminant function[J]. IEEE Transactions on Neural Networks, 1990, 1(4):296-298.
[15] KONG X, ZHANG J, YU P S. Inferring anchor links across multiple heterogeneous social networks[C] // Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. San Francisco: ACM, 2013: 179-188.
[1] 张鹏,王素格,李德玉,王杰. 一种基于启发式规则的半监督垃圾评论分类方法[J]. 山东大学学报(理学版), 2017, 52(7): 44-51.
[2] 黄天意,祝峰. 基于流形学习的代价敏感特征选择[J]. 山东大学学报(理学版), 2017, 52(3): 91-96.
[3] 苏丰龙,谢庆华,黄清泉,邱继远,岳振军. 基于直推式学习的半监督属性抽取[J]. 山东大学学报(理学版), 2016, 51(3): 111-115.
[4] 杜红乐,张燕,张林. 不均衡数据集下的入侵检测[J]. 山东大学学报(理学版), 2016, 51(11): 50-57.
[5] 陈亚东, 洪宇, 杨雪蓉, 王潇斌, 姚建民, 朱巧明. 面向框架语义分析的目标词自动识别方法[J]. 山东大学学报(理学版), 2015, 50(07): 45-53.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 史爱玲1,马明2*,郑莹2. 齐次泊松响应的客户寿命值及性质[J]. 山东大学学报(理学版), 2014, 49(03): 96 -100 .
[2] 田学刚, 王少英. 算子方程AXB=C的解[J]. J4, 2010, 45(6): 74 -80 .
[3] 庞观松,张黎莎,蒋盛益*,邝丽敏,吴美玲. 一种基于名词短语的检索结果多层聚类方法[J]. J4, 2010, 45(7): 39 -44 .
[4] 唐风琴1,白建明2. 一类带有广义负上限相依索赔额的风险过程大偏差[J]. J4, 2013, 48(1): 100 -106 .
[5] 邱桃荣,王璐,熊树洁,白小明. 一种基于粒计算的知识隐藏方法[J]. J4, 2010, 45(7): 60 -64 .
[6] 薛秋芳1,2,高兴宝1*,刘晓光1. H-矩阵基于外推GaussSeidel迭代法的几个等价条件[J]. J4, 2013, 48(4): 65 -71 .
[7] 孙小婷1,靳岚2*. DOSY在寡糖混合物分析中的应用[J]. J4, 2013, 48(1): 43 -45 .
[8] 冒爱琴1, 2, 杨明君2, 3, 俞海云2, 张品1, 潘仁明1*. 五氟乙烷灭火剂高温热解机理研究[J]. J4, 2013, 48(1): 51 -55 .
[9] 任敏1,2,张光辉1. 右半直线上依分布收敛独立随机环境中随机游动的吸收概率[J]. J4, 2013, 48(1): 93 -99 .
[10] 赵君1,赵晶2,樊廷俊1*,袁文鹏1,3,张铮1,丛日山1. 水溶性海星皂苷的分离纯化及其抗肿瘤活性研究[J]. J4, 2013, 48(1): 30 -35 .