基于受限非负张量分解的用户社会影响力分析

doi:10.11959/j.issn.1000-436x.2016125

通信学报 ›› 2016, Vol. 37 ›› Issue (6): 154-162.doi: 10.11959/j.issn.1000-436x.2016125

基于受限非负张量分解的用户社会影响力分析

魏晶晶^1,²,陈畅^3,⁴,廖祥文^3,⁴,陈国龙^3,⁴,程学旗⁵

¹ 福州大学物理与信息工程学院，福建福州 350116
² 福建江夏学院电子信息科学学院，福建福州 350108
³ 福州大学数学与计算机科学学院，福建福州 350116
⁴ 福州大学福建省网络计算与智能信息处理重点实验室，福建福州 350116
⁵ 中国科学院计算技术研究所，北京 100086

出版日期:2016-06-25 发布日期:2017-08-04
基金资助:
国家自然科学基金资助项目;教育部博士点联合基金资助项目;福建省科技重大专项基金资助项目;福州市科技计划基金资助项目;福州市科技计划基金资助项目

User social influence analysis based on constrained nonnegative tensor factorization

Jing-jing WEI^1,²,Chang CHEN^3,⁴,Xiang-wen LIAO^3,⁴,Guo-long CHEN^3,⁴,Xue-qi CHENG⁵

¹ College of Physics and Information Engineering,Fuzhou University,Fuzhou 350116,China
² College of Electronics and Information Science,Fujian Jiangxia University,Fuzhou 350108,China
³ College of Mathematics and Computer Science,Fuzhou University,Fuzhou 350116,China
⁴ Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou University,Fuzhou 350116,China
⁵ Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100086,China

Online:2016-06-25 Published:2017-08-04
Supported by:
The National Natural Science Foundation of China;The Research Fund for Doctoral Program of Higher Education of China;The Key Project of Science and Technology of Fujian;The Project of Science and Technology of Fuzhou;The Project of Science and Technology of Fuzhou

摘要/Abstract

摘要：

针对传统社会影响力分析方法未能充分考虑观点和话题信息等问题，提出了一种基于受限非负张量分解的用户社会影响力分析方法。首先把社交媒介用户相互评论关系自然地表示成三阶张量，然后通过拉普拉斯话题约束矩阵控制张量分解过程，最后根据分解得到的潜在因子度量用户观点社会影响力。该方法的优点是能有效地从受限张量分解结果中检索出给定话题下用户的社会影响力，同时保持其社会影响力的极性分布。实验结果表明，该方法的性能优于OOLAM和TwitterRank等基准算法。

关键词: 社会影响力, 话题, 观点, 张量分析

Abstract:

Existing models for measuring user social influence fail to integrate both opinion and topic information.Therefore,a new constrained nonnegative tensor factorization method combining user’s opinion and the topical relevance was proposed.The method represented user’s comment relations as 3-order tensor,factorized the comments tensor constrained by Laplacian topical matrix,and then measures user influence according to the latent factors resulting from the tensor factorization.Thus,the new method not only was capable to effectively calculate the strength of user social influence on given topic,but also kept the polarity allocation of social influence.The experimental result shows that the performance of the proposed method is better than that of the baseline methods such as OOLAM,TwitterRank,etc.

Key words: social influence, topic, opinion, tensor analysis

魏晶晶,陈畅,廖祥文,陈国龙,程学旗. 基于受限非负张量分解的用户社会影响力分析[J]. 通信学报, 2016, 37(6): 154-162.

Jing-jing WEI,Chang CHEN,Xiang-wen LIAO,Guo-long CHEN,Xue-qi CHENG. User social influence analysis based on constrained nonnegative tensor factorization[J]. Journal on Communications, 2016, 37(6): 154-162.

图/表 10

图1

图2

图3

表1

实验数据描述"

话题	用户间交互关系数量					微博数量
话题	u_d	u_s	$t_{s d}^{+}$	$t_{s d}^{\pm}$	$t_{s d}^{-}$	u_d
篮球	637	34 332	21 190	34 140	8 860	103 767
经济	476	9 841	3 062	7 908	1 932	54 949
法律	486	10 797	3 728	11 319	2 303	60 179
健康	545	9 640	2 826	8 379	979	63 853

表1

图4

表2

图5

表3

表4

图6

参考文献 17

[1]	CUI P , WANG F , YANG S ,et al. Item-level social influence prediction with probabilistic hybrid factor matrix factorization[C]// AAAI. 2011: 331-336.
[2]	CUI P , WANG F , LIU S ,et al. Who should share what?:item-level social influence prediction for users and posts ranking[C]// The 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2011: 185-194.
[3]	RASHID A M , KARYPIS G , RIEDL J . Influence in ratings-based recommender systems:an algorithm- independent approach[C]// The SIAM International Conference on Data Mining. 2005: 556-560.
[4]	BAKSHY E , HOFMAN J M , MASON W A ,et al. Everyone's an influencer:quantifying influence on Twitter[C]// The fourth ACM International Conference on Web Search and Data Mining. ACM, 2011: 65-74.
[5]	YANG J , LESKOVEC J . Modeling information diffusion in implicit networks[C]// 2010 IEEE 10th International Conference on Data Mining(ICDM). IEEE, 2010: 599-608.
[6]	SAKAKI T , OKAZAKI M , MATSUO Y . Earthquake shakes Twitter users:real-time event detection by social sensors[C]// The 19th International Conference on World Wide Web. ACM, 2010: 851-860.
[7]	BAKSHY E , ECKLES D , YAN R ,et al. Social influence in social advertising:evidence from field experiments[C]// The 13th ACM Conference on Electronic Commerce. ACM, 2012: 146-161.
[8]	毛佳昕, 刘奕群, 张敏 ,等. 基于用户行为的微博用户社会影响力分析[J]. 计算机学报, 2014,37(4): 791-800. MAO J X , LIU Y Q , ZHANF M ,et al. Social influence analysis for micro-blog user based on user behavior[J]. Chinese Journal of Computers, 2014,37(4): 791-800.
[9]	吴信东, 李毅, 李磊 . 在线社交网络影响力分析[J]. 计算机学报, 2014,37(4): 735-752. WU X D , LI Y , LI L . Influence analysis of online social networks[J]. Chinese Journal of Computers, 2014,37(4): 735-752.
[10]	WENG J , LIM E P , JIANG J ,et al. Twitterrank:finding topic-sensitive influential twitterers[C]// The Third ACM International Conference on Web Search and Data Mining. ACM, 2010: 261-270.
[11]	CAI K , BAO S , YANG Z ,et al. OOLAM:an opinion oriented link analysis model for influence persona discovery[C]// The fourth ACM International Conference on Web Search and Data Mining. ACM, 2011: 645-654.
[12]	KOLDA T G , BADER B W . Tensor decompositions and applications[J]. SIAM Review, 2009,51(3): 455-500.
[13]	DONG Z D , DONG Q . “ZhiHu”[EB/OL]. .
[14]	CICHOCKI A , ZDUNEK R , PHAN A H ,et al. Nonnegative matrix and tensor factorizations:applications to exploratory multi-way data analysis and blind source separation[M]. John Wiley＆Sons, 2009: 42-46.
[15]	HU X , TANG L , TANG J ,et al. Exploiting social relations for sentiment analysis in microblogging[C]// The Sixth ACM International Conference on Web Search and Data Mining. ACM, 2013: 537-546.
[16]	DAVIDSON I , GILPIN S , WALKER P B . Behavioral event data and their analysis[J]. Data Mining and Knowledge Discovery, 2012,25(3): 635-653.
[17]	KOLDA T G , BADER B W , KENNY J P . Higher-order Web link analysis using multilinear algebra[C]// Fifth IEEE International Conference on Data Mining. IEEE, 2005: 242-249.

方法		篮球			经济			法律			健康
方法	p@5	p@10	p@20	p@5	p@10	p@20	p@5	p@10	p@20	p@5	p@10	p@20
CP	0.00	0.00	0.15	0.40	0.30	0.45	0.20	0.20	0.35	0.20	0.20	0.35
CP+BM25	0.00	0.00	0.10	0.40	0.40	0.45	0.20	0.20	0.35	0.20	0.20	0.40
OOLAM	0.20	0.40	0.55	0.60	0.40	0.35	0.20	0.20	0.40	0.20	0.20	0.40
OOLAM+BM25	0.40	0.50	0.55	0.60	0.50	0.55	0.20	0.40	0.55	0.40	0.50	0.55
TwitterRank	0.00	0.20	0.20	0.20	0.10	0.30	0.00	0.10	0.30	0.20	0.30	0.45
TR+RA	0.40	0.50	0.60	0.60	0.50	0.55	0.20	0.40	0.55	0.40	0.50	0.55
RA	0.40	0.40	0.60	0.60	0.40	0.35	0.20	0.30	0.35	0.20	0.20	0.40
FA	0.40	0.50	0.35	0.80	0.70	0.50	0.20	0.60	0.45	0.40	0.30	0.40
本文	0.60	0.60	0.60	0.60	0.60	0.55	0.40	0.30	0.45	0.60	0.50	0.65

基于受限非负张量分解的用户社会影响力分析

User social influence analysis based on constrained nonnegative tensor factorization

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 17

相关文章 15

Metrics

推荐阅读 0

话题	Kappa指标
法律	0.737 574 1
健康	0.620 422 2
经济	0.719 395 0
篮球	0.680 719 3

话题	Pearson相关系数
篮球	0.705 0
经济	0.818 3
法律	0.814 3
健康	0.853 5

[1]	李骜, 王卓, 于晓洋, 陈德运, 张英涛, 孙广路. 多核低冗余表示学习的稳健多视图子空间聚类方法[J]. 通信学报, 2021, 42(11): 193-204.
[2]	邓璐,贾焰,方滨兴,周斌,张涛,刘心. 分布式环境下话题发现算法性能分析[J]. 通信学报, 2018, 39(8): 176-184.
[3]	石磊,杜军平,梁美玉. 基于RNN和主题模型的社交网络突发话题发现[J]. 通信学报, 2018, 39(4): 189-198.
[4]	贺敏,徐杰,杜攀,程学旗,王丽宏. 基于时间序列分析的微博突发话题检测方法[J]. 通信学报, 2016, 37(3): 48-54.
[5]	陈福,林闯,薛超,徐月梅,孟坤,倪艺函. 短句语义向量计算方法[J]. 通信学报, 2016, 37(2): 11-19.
[6]	张光磊，徐雅斌. 面向热门话题的微博观点挖掘方法[J]. 通信学报, 2014, 35(Z2): 30-227.
[7]	张光磊,徐雅斌. 面向热门话题的微博观点挖掘方法[J]. 通信学报, 2014, 35(Z2): 220-227.
[8]	程俊霞,李芝棠,邹明光,肖津. 基于SVM过滤的微博新闻话题检测方法[J]. 通信学报, 2013, 34(Z2): 74-78.
[9]	赖清楠,马皓,宋维佳,李婷婷,蒋广学,张蓓. 高校BBS与微博的用户社交行为特征分析[J]. 通信学报, 2013, 34(Z2): 99-106.
[10]	程俊霞1，李芝棠1,2，邹明光1，肖津1. 基于SVM过滤的微博新闻话题检测方法[J]. 通信学报, 2013, 34(Z2): 15-78.
[11]	赖清楠1，马皓2，宋维佳2，李婷婷3，蒋广学3，张蓓2. 高校BBS与微博的用户社交行为特征分析[J]. 通信学报, 2013, 34(Z2): 20-106.
[12]	王巍1，李锐光2，周渊2，杨武1. 基于用户与节点规模的微博突发话题传播预测算法[J]. 通信学报, 2013, 34(Z1): 11-91.
[13]	贺敏1,2，王丽宏2，杜攀1，张瑾1，程学旗1. 基于有意义串聚类的微博热点话题发现方法[J]. 通信学报, 2013, 34(Z1): 34-262.
[14]	贺敏,王丽宏,杜攀,张瑾,程学旗. 基于有意义串聚类的微博热点话题发现方法[J]. 通信学报, 2013, 34(Z1): 256-262.
[15]	王巍,李锐光,周渊,杨武. 基于用户与节点规模的微博突发话题传播预测算法[J]. 通信学报, 2013, 34(Z1): 84-91.