Please wait a minute...
文章检索
复杂系统与复杂性科学  2023, Vol. 20 Issue (2): 1-9    DOI: 10.13306/j.1672-3813.2023.02.001
  本期目录 | 过刊浏览 | 高级检索 |
网络直播大数据:统计特征与时序规律挖掘
郭淑慧, 吕欣
国防科技大学系统工程学院, 长沙 410073
Data Mining of Live Streaming Platforms: Statistical Characteristics and Temporal Pattern
GUO Shuhui, LÜ Xin
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
全文: PDF(3503 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 为挖掘网络直播领域数百万主播与数亿计观众的活跃互动下大规模人群行为学特征,以斗鱼和虎牙直播平台为例,统计分析了连续123天、涉及240多万名主播、超过7.26亿条的直播数据,总结了直播平台的负载时序规律和用户行为特征。发现直播负载存在明显的日内效应和周内效应,不同直播模式的主播在观众数、粉丝数等统计特征上存在显著的组间差异,主播生存期和直播间观众数量符合幂律分布,随着平台发展,主播和观众数量呈现较强的线性相关性,但其波动性也逐步增大,体现出系统越来越强的异质性和非均匀性。对理解网络直播复杂系统中的用户行为模式、挖掘用户分布规律及变化趋势、设计商业模式如个性化推荐等方面具有重要意义。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
郭淑慧
吕欣
关键词 网络直播直播平台大数据流量分析行为动力学    
Abstract:To explore the behavioral characteristics of massive crowds under the active interaction of millions of streamers and viewers in the field of live streaming, this paper summarized the temporal patterns of live streaming workload and user behavior characteristics of the live streaming platform, taking Douyu and Huya live streaming platforms as examples, a statistical analysis of 123 consecutive days, involving more than 2.4 million anchors, and more than 726 million live streaming data. The live streaming workload has obvious intra-day and intra-week effect. Different live streaming modes have significant differences in live streaming characteristics such as the average number of viewers and followers. The lifetime of streamers and the number of viewers conform to a power law distribution. With the development of the platform, there is a strong linear correlation between the number of streamers and viewers, but its volatility is gradually increasing, reflecting the increasingly strong heterogeneity and non-uniformity of the system. It is of great significance for understanding user behavior patterns in complex systems of live streaming, mining user distribution laws and changing trends, and designing business models such as personalized recommendations.
Key wordslive streaming    live streaming platform    big data    workload analysis    behavioral dynamics
收稿日期: 2021-09-06      出版日期: 2023-07-21
ZTFLH:  TP391  
  G358  
基金资助:国家杰出青年科学基金(72025405);国家自然科学基金重大研究计划(91846301);国家社科基金重大项目(22ZDA102)
通讯作者: 吕欣(1984-),男,博士,教授,主要研究方向为大数据挖掘、复杂网络、应急管理、人类行为动力学。   
作者简介: 郭淑慧(1996-),女,博士研究生,主要研究方向为社交媒体大数据分析挖掘。
引用本文:   
郭淑慧, 吕欣. 网络直播大数据:统计特征与时序规律挖掘[J]. 复杂系统与复杂性科学, 2023, 20(2): 1-9.
GUO Shuhui, LÜ Xin. Data Mining of Live Streaming Platforms: Statistical Characteristics and Temporal Pattern. Complex Systems and Complexity Science, 2023, 20(2): 1-9.
链接本文:  
https://fzkx.qdu.edu.cn/CN/10.13306/j.1672-3813.2023.02.001      或      https://fzkx.qdu.edu.cn/CN/Y2023/V20/I2/1
[1] CHEN X, CHEN S, WANG X, et al. " I was afraid, but now I enjoy being a streamer!" understanding the challenges and prospects of using live streaming for online education[J]. Proceedings of the ACM on Human-Computer Interaction, 2021, 4(CSCW3): 1-32.
[2] LIU L, AREMU E O, YOO D. Brand marketing strategy of live streaming in mobile era: a case study of tmall platform[J]. Journal of East Asia Management, 2020, 1(1): 65-87.
[3] LU Z, ANNETT M, FAN M, et al. " I feel it is my responsibility to stream" streaming and engaging with intangible cultural heritage through livestreaming[C]// BREWSTER S, FITZPATRICK G, COX A, et al. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. Scotland, UK: ACM, 2019: 1-14.
[4] FAN H, LEE F L F. Judicial visibility under responsive authoritarianism: a study of the live broadcasting of court trials in China[J]. Media, Culture & Society, 2019, 41(8): 1088-1106.
[5] 中国互联网网络信息中心. 第49次中国互联网络发展状况统计报告[EB/OL]. [2022-07-04]. http://www.cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/202202/P020220311493378715650.pdf.
CENTER C I N I. The 49th statistical report on internet development in China[EB/OL]. [2022-07-04].http://www.cnnic.net.cn/hlwfzyj/hlwxzbg/hlwtjbg/202202/P020220311493378715650.pdf.
[6] 艾媒咨询. 2021Q3中国在线直播行业研究报告[EB/OL]. [2022-07-04]. https://www.iimedia.cn/c400/81868.html.
CONSULTING I R. 2021Q3 China online live streaming industry research report[EB/OL]. [2022-07-04].https://www.iimedia.cn/c400/81868.html.
[7] CLAYPOOL M, FARRINGTON D, MUESCH N. Measurement-based analysis of the video characteristics of twitch. tv[C]// BERRY J, BERTOZZI E, FIELLIN L, et al. 2015 IEEE Games Entertainment Media Conference (GEM). Toronto, Canada: IEEE, 2015: 1-4.
[8] PIRES K, SIMON G. YouTube live and twitch: a tour of user-generated live streaming systems[C]// OOI W T, FENG W-C, LIU F. Proceedings of the 6th ACM Multimedia Systems Conference. Oregon, USA: ACM, 2015: 225-230.
[9] ZHU Z H, YANG Z, DAI Y F. Understanding the gift-sending interaction on live-streaming video websites[C]// MEISELWITZ G. International Conference on Social Computing and Social Media. Vancouver, Canada: Springer, 2017: 274-285.
[10] NASCIMENTO G, RIBEIRO M, CERF L, et al. Modeling and analyzing the video game live-streaming community[C]// BAEZA-YATES R. 2014 9th Latin American Web Congress. Minas Gerais, Brazil: IEEE, 2014: 1-9.
[11] ZHAO J, MA M, GONG W, et al. Social media stickiness in mobile personal livestreaming service[C]// LAB C. 2017 IEEE/ACM 25th International Symposium on Quality of Service (IWQoS). Vilanova i la Geltrú, Spain: IEEE, 2017: 1-2.
[12] PIRES K, SIMON G. Dash in twitch: adaptive bitrate streaming in live game streaming platforms[C]// HASSAN M, BEGEN A C, TIMMERER C. Proceedings of the 2014 Workshop on Design, Quality and Deployment of Adaptive Video Streaming. Sydney, Australia: ACM, 2014: 13-18.
[13] ZHANG C, LIU J. On crowdsourced interactive live streaming: a twitch. tv-based measurement study[C]// FENG W-C, ZINK M. Proceedings of the 25th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video. Oregon, USA: ACM, 2015: 55-60.
[14] HAMILTON W A, GARRETSON O, KERNE A. Streaming on twitch: fostering participatory communities of play within live mixed media[C]// JONES M, PALANQUE P, SCHMIDT A, et al. Proceedings of the 32nd annual ACM Conference on Human Factors in Computing Systems. Toronto, Canada: ACM, 2014: 1315-1324.
[15] LYKOUSAS N, GóMEZ V, PATSAKIS C. Adult content in social live streaming services: characterizing deviant users and relationships[C]// BRANDES U, REDDY C, TAGARELLI A. 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). Barcelona, Spain: IEEE, 2018: 375-382.
[16] 郭淑慧, 吕欣. 网络直播平台数据挖掘与行为分析综述[J]. 物理学报, 2020, 69(8): 117-126.
GUO S, LU X. Live streaming: data mining and behavior analysis[J].Acta Physica Sinica, 2020, 69(8): 117-126.
[17] BORGES A, GOMES P, NACIF J, et al. Characterizing sopcast client behavior[J]. Computer Communications, 2012, 35(8): 1004-1016.
[18] VELOSO E, ALMEIDA V, MEIRA W, et al. A hierarchical characterization of a live streaming media workload[C]// KüHLEWIND M, KUTSCHER D. Proceedings of the 2nd ACM SIGCOMM Workshop on Internet measurment. Marseille France: ACM, 2002: 117-130.
[19] DENG J, CUADRADO F, TYSON G, et al. Behind the game: exploring the twitch streaming platform[C]// NETGAMES. 2015 International Workshop on Network and Systems Support for Games (NetGames). Zagreb, Croatia: IEEE, 2015: 1-6.
[20] JIA A L, SHEN S, EPEMA D H, et al. When game becomes life: the creators and spectators of online game replays and live streaming[J]. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2016, 12(4): 47.
[21] FALLICA B, LU Y, KUIPERS F, et al. On the quality of experience of SopCast[C]// AT-BEGAIN K, CUEVAS A. 2008 The Second International Conference on Next Generation Mobile Applications, Services, and Technologies. Cardiff, Hnited Kingdom: IEEE, 2008: 501-506.
[22] 中国信息通信研究院. 2018下半年中国网络直播行业景气指数及短视频报告[EB/OL]. [2022-07-04]. http://www.caict.ac.cn/kxyj/qwfb/ztbg/201907/P020190711347399467992.pdf.
TECHNOLOGY C A O I A C. China's online live streaming industry prosperity index and short video report in the second half of 2018[EB/OL]. [2022-07-04].http://www.caict.ac.cn/kxyj/qwfb/ztbg/201907/P020190711347399467992.pdf.
[23] KHADEMALOMOOM S, NARAYAN P K. Intraday effects of the currency market[J]. Journal of International Financial Markets, Institutions and Money, 2019, 58(1): 65-77.
[24] PINK D H. When: The Scientific Secrets of Perfect Timing[M]. New York: Penguin Press, 2019: 15-20.
[25] HINES C B. Time-of-day effects on human performance[J]. Journal of Catholic Education, 2004, 7(3): 390-413.
[26] BERNARD T, GIACOMONI M, GAVARRY O, et al. Time-of-day effects in maximal anaerobic leg exercise[J]. European Journal of Applied Physiology and Occupational Physiology, 1997, 77(1-2): 133-138.
[27] MÜLLER U A, DACOROGNA M M, OLSEN R B, et al. Statistical study of foreign exchange rates, empirical evidence of a price change scaling law, and intraday analysis[J]. Journal of Banking & Finance, 1990, 14(6): 1189-1208.
[28] STOHR D, LI T, WILK S, et al. An analysis of the YouNow live streaming platform[C]// KANHERE S, TöLLE J, CHERKAOUI S. 2015 IEEE 40th Local Computer Networks Conference Workshops (LCN Workshops). Florida, USA: IEEE, 2015: 673-679.
[29] GUPTA S, HANSSENS D, HARDIE B, et al. Modeling customer lifetime value[J]. Journal of service research, 2006, 9(2): 139-155.
[30] SRIPANIDKULCHAI K, MAGGS B, ZHANG H. An analysis of live streaming workloads on the internet[C]// LOMBARDO A, KUROSE J. Proceedings of the 4th ACM SIGCOMM conference on Internet measurement. Sicily, Italy: ACM, 2004: 41-54.
[31] 樊超, 郭进利, 韩筱璞, 等. 人类行为动力学研究综述[J]. 复杂系统与复杂性科学, 2011, 8(2): 1-17.
FAN C, GUO J, HAN X, et al. A review of research on human dynamics[J]. Complex Systems and Complexity Science, 2011, 8(2): 1-17.
[32] 李爽, 陈亚荣. 网络直播环境下人际互动对用户行为意愿的影响研究[J]. 中国市场, 2018, 1(7): 18-20.
LI S, CHEN Y. Research on the influence of interpersonal interaction on user behavior intention in the environment of online live streaming[J]. China Market, 2018, 1(7): 18-20.
[33] LILJEROS F, EDLING C R, AMARAL L A, et al. The web of human sexual contacts[J]. Nature, 2001, 411(6840): 907-8.
[34] BARÁBASI A L, ALBERT R. Emergence of scaling in random networks[J]. Science, 1999, 286(5439): 509-12.
[35] REDNER S. How popular is your paper? An empirical study of the citation distribution[J]. European Physical Journal B Condensed Matter Physics,1998,4(2): 131-134.
[36] REPETOWICZ P, HUTZLER S, RICHMOND P. Dynamics of money and income distributions[J]. Physica A: Statistical Mechanics and Its Applications, 2005, 356(2-4): 641-654.
[37] ALMEIDA J M, KRUEGER J, EAGER D L, et al. Analysis of educational media server workloads[C]// NIEH J. Proceedings of the 11th International Workshop on Network and Operating Systems Support for Digital Audio and Video. New York, USA: ACM, 2001: 21-30.
[38] DA SILVA D F C, NETO R D M S. Population dynamics and spatial dependence: evidence from Brazilian cities[J]. Review of Regional Studies, 2019, 49(3): 454-473.
[39] GUO Q, GAO L. Distribution of individual incomes in China between 1992 and 2009[J]. Physica A: Statistical Mechanics and Its Applications, 2012, 391(21): 5139-5145.
[1] 朱懋昌, 宾晟, 孙更新. 基于COVID-19传播特性的传染病模型的构建与研究[J]. 复杂系统与复杂性科学, 2023, 20(2): 29-37.
[2] 张书谙, 王曦, 代继鹏, 隋毅, 孙仁诚. 基于关键词共现网络的主题词提取算法[J]. 复杂系统与复杂性科学, 2023, 20(1): 74-80.
[3] 王佳亮, 李海滨, 李海燕. 基于复杂网络的新冠病毒群体免疫数值仿真[J]. 复杂系统与复杂性科学, 2023, 20(1): 27-33.
[4] 王一伊, 卜凡亮. 涉恐个体极端思想演化双阈值观点动力学模型[J]. 复杂系统与复杂性科学, 2022, 19(4): 55-63.
[5] 王浩, 许小可. 融合文本和表情符号特征的社交网络用户性别识别[J]. 复杂系统与复杂性科学, 2022, 19(4): 17-24.
[6] 赵薇, 李建波, 吕志强, 董传浩. 融合时间和地理信息的兴趣点推荐研究[J]. 复杂系统与复杂性科学, 2022, 19(4): 25-31.
[7] 李军涛, 胡启贤, 刘朋飞, 郭文文. 跨层穿梭车双提升机系统多目标问题优化[J]. 复杂系统与复杂性科学, 2022, 19(4): 80-90.
[8] 李冯, 宾晟, 孙更新. 基于时变参数的SCUIR传播模型的构建与研究[J]. 复杂系统与复杂性科学, 2022, 19(2): 80-86.
[9] 胡亮, 肖人彬, 王英聪. 蜂群激发抑制算法及其在交通信号配时中的应用[J]. 复杂系统与复杂性科学, 2019, 16(2): 9-18.
[10] 刘琪, 肖人彬. 观点动力学视角下基于意见领袖的网络舆情反转研究[J]. 复杂系统与复杂性科学, 2019, 16(1): 1-13.
[11] 李甍娜, 郭进利, 卞闻, 常宁戈, 肖潇, 陆睿敏. 网络视角下的唐诗[J]. 复杂系统与复杂性科学, 2017, 14(4): 66-71.
[12] 蒲玮, 李雄. 基于能力组件的作战仿真Agent模块化结构设计[J]. 复杂系统与复杂性科学, 2017, 14(3): 45-57.
[13] 崔琼, 李建华, 冉淏丹, 南明莉. 任务流驱动的指挥信息系统动态超网络模型[J]. 复杂系统与复杂性科学, 2017, 14(3): 58-67.
[14] 杨晓波, 陈楚湘, 王至婉. 基于节点相似性的LFM社团发现算法[J]. 复杂系统与复杂性科学, 2017, 14(3): 85-90.
[15] 瞿倩倩, 韩华, 吕亚楠, 贾承丰, 马媛媛. 基于社交网络结构特征的S2IR谣言传播模型[J]. 复杂系统与复杂性科学, 2019, 16(3): 48-59.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
Baidu
map