TSL：基于连接强度的Facebook消息流行度预测模型

doi:10.11959/j.issn.1000-436x.2019207

通信学报 ›› 2019, Vol. 40 ›› Issue (10): 1-9.doi: 10.11959/j.issn.1000-436x.2019207

• 学术论文 • 下一篇

TSL：基于连接强度的Facebook消息流行度预测模型

王晓萌¹, 方滨兴^1,², 张宏莉¹, 王星¹

¹ 哈尔滨工业大学计算机网络与信息安全技术研究中心，黑龙江哈尔滨 150001
² 广州大学网络空间先进技术研究院，广东广州 510006

修回日期:2019-08-30 出版日期:2019-10-25 发布日期:2019-11-07
作者简介:王晓萌（1987- ），男，黑龙江哈尔滨人，哈尔滨工业大学博士生，主要研究方向为在线社交网络、信息传播预测、舆情安全等。|方滨兴（1960- ），男，江西万年人，中国工程院院士，哈尔滨工业大学教授、博士生导师，主要研究方向为计算机网络与信息安全理论与技术、并行计算等。|张宏莉（1973- ），女，吉林榆树人，博士，哈尔滨工业大学教授、博士生导师，主要研究方向为网络与信息安全、网络测量与建模、网络计算、并行处理等。|王星（1981- ），男，重庆人，博士，哈尔滨工业大学助理研究员，主要研究方向为网络与信息安全、网络舆情监控、知识迁移。
基金资助:
国家重点研发计划基金资助项目(2017YFB0803305);国家重点研发计划基金资助项目(2016QY03D0501)

TSL:predicting popularity of Facebook content based on tie strength

Xiaomeng WANG¹, Binxing FANG^1,², Hongli ZHANG¹, Xing WANG¹

¹ Research Center of Computer Network and Information Security Technology,Harbin Institute of Technology,Harbin 150001,China
² Cyberspace Institute of Advanced Technology,Guangzhou University,Guangzhou 510006,China

Revised:2019-08-30 Online:2019-10-25 Published:2019-11-07
Supported by:
The National Key R＆D Program of China(2017YFB0803305);The National Key R＆D Program of China(2016QY03D0501)

摘要/Abstract

摘要：

在线社交网络的迅速发展使信息呈现爆炸式增长，然而不同消息的流行度存在较大差异，对其准确预测一直是领域内的研究难点。流行度预测的任务是根据消息传播早期过程中涌现的特征预测其未来的传播趋势，现有基于传播网络特征与拟合函数的预测模型难以解决预测准确率低的问题，因此借助社会学中的弱连接理论，引入连接强度的概念，并融合消息传播早期的流行度构建多元线性回归方程，提出了一种针对 Facebook 知名主页的消息流行度的预测模型TSL。通过在Facebook真实数据集（含154万次转发）上与其他具有代表性的基准模型进行比较，实验表明TSL模型可以对消息的最终转发流行度进行有效预测，预测性能优于同类方法。

关键词: 在线社交网络, 弱连接, 流行度, 信息传播

Abstract:

The rapid development of online social networks leads to an explosion of information,however,there are great differences in the popularity of different messages,and accurate prediction is always a great difficulty is the current study.Popularity prediction of online content aims to predict the popularity in the future based on its early diffusion status.Existing models for popularity prediction were mostly based on discovering network features or fitting the equation into a varying time function that the accuracy of current popularity prediction model was not high enough.Therefore,with the help of the weak ties theory in sociology,the concept of tie strength was introduced and a multilinear regression equation was constructed combined with the early popularity.A TSL model to predict the popularity of Facebook’s well-known pages was proposed.The main contribution of this article was to solve the problem and few or no work based on sociology.A high linear correlation between the proportion of faithful fans was existed in Facebook homepage with frequent shares in the early and the future popularity.Compared with other baseline models,an experimental study of Facebook (including 1.54 million shares) illustrates the effectiveness of the proposed TSL model,and the performance is better than the existing similar methods.

Key words: online social networks, weak ties, popularity, information diffusion

中图分类号:

TP393

王晓萌, 方滨兴, 张宏莉, 王星. TSL：基于连接强度的Facebook消息流行度预测模型[J]. 通信学报, 2019, 40(10): 1-9.

Xiaomeng WANG, Binxing FANG, Hongli ZHANG, Xing WANG. TSL:predicting popularity of Facebook content based on tie strength[J]. Journal on Communications, 2019, 40(10): 1-9.

图/表 9

图1

表1

图2

图3

图4

图5

图6

表2

图7

参考文献 23

[1]	HUIJBOOM N , VAN DEN BROEK T , FRISSEN V ,et al. Key areas in the public sector impact of social computing[J].,2009,3. European Communities, 2009,3.
[2]	GUPTA M , GAO J , ZHAI C X ,et al. Predicting future popularity trend of events in microblogging platforms[J]. Proceedings of the American Society for Information Science and Technology, 2012,49(1): 1-10.
[3]	ZHAO Y , QIN B , LIU T ,et al. Social sentiment sensor:a visualization system for topic detection and topic sentiment analysis on microblog[J]. Multimedia Tools and Applications, 2016,75(15): 8843-8860.
[4]	BORAH P . Political Facebook use:campaign strategies used in 2008 and 2012 presidential elections[J]. Journal of Information Technology＆ Politics, 2016,13(4): 326-338.
[5]	ALBERT-LASZLO B , REKA A . Emergence of scaling in random networks[J]. Science, 1999,286(5439): 509-512.
[6]	KWAK H , LEE C , PARK H ,et al. What is Twitter,a social network or a news media?[C]// Proceedings of the 19th International Conference on World Wide Web. ACM, 2010: 591-600.
[7]	GOLDER S A , WILKINSON D M , HUBERMAN B A . Rhythms of social interaction:messaging within a massive online network[C]// Communities and Technologies 2007. Springer, 2007: 41-66.
[8]	SZABO G , HUBERMAN B A . Predicting the popularity of online content[J]. Communications of the ACM, 2010,53(8): 80-88.
[9]	FRIEDKIN N E . Information flow through strong and weak ties in intraorganizational social networks[J]. Social Networks, 1982,3(4): 273-285.
[10]	ABDULLAH S , WU X D . An epidemic model for news spreading on twitter[C]// 2011 23rd IEEE International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2011: 163-169.
[11]	MATSUBARA Y , SAKURAI Y , PRAKASH B A ,et al. Rise and fall patterns of information diffusion:model and implications[C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2012: 6-14.
[12]	LI H , MA X , WANG F ,et al. On popularity prediction of videos shared in online social networks[C]// Proceedings of the 22nd ACM International Conference on Information ＆ Knowledge Management. ACM, 2013: 169-178.
[13]	CHANG B , ZHU H , GE Y ,et al. Predicting the popularity of online serials with autoregressive models[C]// Proceedings of the 23rd ACM International Conference on Information and Knowledge Management. ACM, 2014: 1339-1348.
[14]	BAO P , SHEN H W , HUANG J ,et al. Popularity prediction in microblogging network:a case study on sina weibo[C]// Proceedings of the 22nd International Conference on World Wide Web. ACM, 2013: 177-178.
[15]	KIM Y . Convolutional neural networks for sentence classification[J]. arXiv Preprint,arXiv:1408.5882, 2014.
[16]	CHENG J , ADAMIC L , DOW P A ,et al. Can cascades be predicted?[C]// Proceedings of the 23rd International Conference on World Wide Web. ACM, 2014: 925-936.
[17]	朱海龙, 云晓春, 韩志帅 . 基于传播加速度的微博流行度预测方法[J]. 计算机研究与发展, 2018,55(6): 1282-1293.
	ZHU H L , YUN X C , HAN Z S . Weibo popularity prediction method based on propagation acceleration[J]. Journal of Computer Research and Development, 2018,55(6): 1282-1293.
[18]	CRANE R , SORNETTE D . Robust dynamic classes revealed by measuring the response function of a social system[J]. Proceedings of the National Academy of Sciences, 2008,105(41): 15649-15653.
[19]	YANG J , LESKOVEC J . Patterns of temporal variation in online media[C]// Proceedings of the Fourth ACM International Conference on Web Search and Data Mining. ACM, 2011: 177-186.
[20]	LERMAN K , HOGG T . Using a model of social dynamics to predict popularity of news[C]// Proceedings of the 19th International Conference on World Wide Web. ACM, 2010: 621-630.
[21]	GAO S , MA J , CHEN Z . Modeling and predicting retweeting dynamics on microblogging platforms[C]// Proceedings of the Eighth ACM International Conference on Web Search and Data Mining. ACM, 2015: 107-116.
[22]	FERRARA E , DE MEO P , FIUMARA G ,et al. The role of strong and weak ties in Facebook:a community structure perspective[J]. arXiv Preprint,arXiv:1203.0535, 2012.
[23]	BAO P , SHEN H W , JIN X ,et al. Modeling and predicting popularity dynamics of microblogs using self-excited hawkes processes[C]// Proceedings of the 24th International Conference on World Wide Web. ACM, 2015: 9-10.

主页	类别	消息总数/条	转发数/次	点赞数/次
Geographic	A	256	177 130	469 498
History	A	474	76 022	168 570
NBA	A	714	330 728	849 734
Call of Duty	B	294	38 357	122 610
Grey’s Anatomy	B	360	64 571	288 365
Fox News	A	562	215 803	570 201
The Simpsons	B	395	157 205	390 057
Will Smith	B	151	144 793	451 108
Barack Obama	A	248	211 807	498 824
Harry Potter	B	321	120 824	429 731

主页	RMSE	r	f	转发用户数
Geographic	0.278 325 94	0.854 637 37	1.9%	177 130
History	0.327 377 78	0.800 401 19	2.4%	76 022
NBA	0.286 945 86	0.877 307 71	9.5%	330 728
Call of Duty	0.191 666 00	0.937 414 42	0.4%	38 357
Grey’s Anatomy	0.261 488 96	0.858 801 76	0.7%	64 571
Fox News	0.308 733 30	0.851 034 12	1.8%	215 803
The Simpsons	0.246 806 58	0.903 169 68	0.4%	157 205
Will Smith	0.217 223 48	0.902 040 75	0.3%	144 793
Harry Potter	0.195 716 76	0.889 507 83	0.1%	120 824
Barack Obama	0.288 655 17	0.766 377 99	1.7%	211 807

TSL：基于连接强度的Facebook消息流行度预测模型

TSL:predicting popularity of Facebook content based on tie strength

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 23

相关文章 15

Metrics

推荐阅读 0

[1]	邹晓红, 许成伟, 陈晶, 宋彪, 王明月. 大规模时序图中种子节点挖掘算法研究[J]. 通信学报, 2022, 43(9): 157-168.
[2]	哈冠雄, 贾巧雯, 陈杭, 贾春福. 无第三方服务器的基于数据流行度的加密去重方案[J]. 通信学报, 2022, 43(8): 17-29.
[3]	蔡艳, 吴凡, 朱洪波. D2D协作边缘缓存系统中基于传输时延的缓存策略[J]. 通信学报, 2021, 42(3): 183-189.
[4]	陈晶,祁子怡. 基于时序关系的社交网络影响最大化算法研究[J]. 通信学报, 2020, 41(10): 211-221.
[5]	蒋雁翔,夏骋宇. 雾无线接入网中的多层协作缓存方法[J]. 通信学报, 2019, 40(9): 116-123.
[6]	彭舰,王屯屯,陈瑜,刘唐,徐文政. 基于跨平台的在线社交网络用户推荐研究[J]. 通信学报, 2018, 39(3): 147-158.
[7]	全拥,贾焰,张良,朱争,周斌,方滨兴. 在线社交网络个体影响力算法测试与性能评估[J]. 通信学报, 2018, 39(10): 1-10.
[8]	刘蓉,陈波,于泠,刘亚尚,陈思远. 恶意社交机器人检测技术研究[J]. 通信学报, 2017, 38(Z2): 197-210.
[9]	李凤华,王彦超,殷丽华,谢绒娜,熊金波. 面向网络空间的访问控制模型[J]. 通信学报, 2016, 37(5): 9-20.
[10]	陈龙,汤红波,罗兴国,柏溢,张震. 基于收益感知的信息中心网络缓存机制[J]. 通信学报, 2016, 37(5): 130-142.
[11]	聂华,张敏,郭敬荣,阳小龙. 基于内容流行度差异性的CDN-P2P融合分发网络缓存替换机制研究[J]. 通信学报, 2015, 36(Z1): 9-15.
[12]	陈侃,陈亮,朱培栋,熊岳山. 基于交互行为的在线社会网络水军检测方法[J]. 通信学报, 2015, 36(7): 120-128.
[13]	刘衍珩1,2，李飞鹏1,2，孙鑫1,2，朱建启1,2. 基于信息传播的社交网络拓扑模型[J]. 通信学报, 2013, 34(4): 1-9.
[14]	刘衍珩,李飞鹏,孙鑫,朱建启. 基于信息传播的社交网络拓扑模型[J]. 通信学报, 2013, 34(4): 1-9.
[15]	于洪,杨显. 微博中节点影响力度量与传播路径模式研究[J]. 通信学报, 2012, 33(Z1): 96-102.