Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (11): 108-119    DOI: 10.11925/infotech.2096-3467.2019.0061
     研究论文 本期目录 | 过刊浏览 | 高级检索 |
社交媒体用户交互行为与股票市场的关联分析研究: 基于新浪财经博客的实证
王欣瑞,何跃()
四川大学商学院 成都 610064
Predicting Stock Market Fluctuations with Social Media Behaviors: Case Study of Sina Finance Blog
Xinrui Wang,Yue He()
Business School, Sichuan University, Chengdu 610064, China
全文: PDF(1061 KB)   HTML ( 10
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】探究社交媒体用户交互行为的社会网络与股市之间的关系, 检验社会网络属性对股市的预测能 力。【方法】利用新浪财经博客的转载信息, 设置时间快照构建多个网络图; 提取网络属性并与上证指数做相关性分析; 最后将具有相关性的网络属性与上证指数进行格兰杰因果关系检验。【结果】网络密度与上证指数呈现二次项关系, 极值点为3 400; 博主节点的平均点赞数与上证指数呈现正相关性, 相关系数为0.486; 平均点赞数取一阶滞后具有协整关系, 可以作为上证指数的格兰杰因。【局限】由于长文本情感分析和算法优化的问题, 未计算博文的情感且所选取的网络属性均为基本属性。【结论】本文验证了社交媒体用户的交互行为对股市的预测能力, 交互行为的社会网络属性能够提高股市预测的精度。

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
王欣瑞
何跃
关键词 用户行为社会网络新浪财经博客相关性分析格兰杰因果关系检验    
Abstract

[Objective] This paper explores the relationship between stock market fluctuations and social media users’ interactive behaviors, aiming to predict the stock prices with social data. [Methods] Firstly, we set snapshots and constructed several social networks by crawling the quotes of Sina Finance Blogs. Then, we extracted the topological features and conducted correlation analysis between the topological features and Shanghai Composite Index. Finally, we used the Granger causality test to further examine the relationship between Shanghai Composite Index and the correlated features. [Results] There was a relationship of quadratic term between graph Density and Shanghai Composite Index, and the extreme point was 3,400. There was a positive correlation between blog Nodes’ average number of likes and Shanghai Composite Index (correlation coefficient = 0.486). Taking the first order lag, the average number of likes can be the Granger cause of Shanghai Composite Index. [Limitations] We did not caculate the emotional scores of the blogs and only extracted the basic topological features. [Conclusions] Users’ social network behaviors could help us predict the changes of stock market.

Key wordsUsers’ Behavior;    Social Networks    Sina Finance Blog    Correlation Analysis    Granger Causality Test
收稿日期: 2019-01-14     
中图分类号:  G353.1  
通讯作者: 何跃     E-mail: 402216179@qq.com
引用本文:   
王欣瑞,何跃. 社交媒体用户交互行为与股票市场的关联分析研究: 基于新浪财经博客的实证[J]. 数据分析与知识发现, 2019, 3(11): 108-119.
Xinrui Wang,Yue He. Predicting Stock Market Fluctuations with Social Media Behaviors: Case Study of Sina Finance Blog. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2019.0061.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2019.0061
图1  不同网络结构的密度
参数名称 解释
平均节点度 网络结构基本属性
密度 用户所关注博主的多样性
平均边权重 用户对关注博主的专一程度
平均阅读量 博主的影响力
平均点赞数 受众对博客文章的认可度
表1  网络参数的现实意义
时间 当月至少发表过一篇博文的
博主的数量
博文总数量 时间 当月至少发表过一篇博文的
博主的数量
博文总数量
2016,1 48 1 132 2017,1 71 2 415
2016,2 53 1 458 2017,2 69 2 885
2016,3 56 1 497 2017,3 74 2 641
2016,4 56 1 587 2017,4 76 2 746
2016,5 61 1 738 2017,5 77 3 068
2016,6 64 1 957 2017,6 78 2 837
2016,7 64 2 049 2017,7 80 2 886
2016,8 66 2 012 2017,8 77 2 822
2016,9 71 1 905 2017,9 76 2 236
2016,10 65 2 521 2017,10 75 2 902
2016,11 66 2 614 2017,11 76 2 919
2016,12 68 2 299 2017,12 78 2 848
表2  数据集描述
图2  部分博主的子图
图3  网络结构属性时间序列
图4  MA·MA3时间序列
控制变量 变量 MA·MA3
相关性 显著性
Average Read、Average Like、Nodes Counts、Edges Counts、Density Average Edges Weight -.442 .058
Average Like、Nodes Counts、Edges Counts、Average Edges Weight、Density Average Read -.406 .084
Edges Counts、Average Edges Weight、Density、Average Read、Average Like Nodes Counts -.434 .063
Average Edges Weight、Nodes Counts、Density、Average Read、Average Like Edges Counts .247 .307
Average Read、Average Like、Nodes Counts、Edges Counts、Average Edges Weight Density -.508 .026*
Nodes Counts、Edges Counts、Average Edges Weight、Density、Average Read Average Like .486 .035*
表3  偏相关分析结果
均方和 自由度 均方 F统计量 显著性
MA·MA3与
密度回归分析
回归 .000 2 .000 8.071 .003
残差 .000 21 .000
总体 .000 23
未标准化系数 标准误差 标准化系数 t统计量 显著性
MA·MA3 -4.526E-5 .000 -42.849 -2.760 .012
MA·MA3 ** 2 6.637E-9 .000 42.367 . .
常数 .078 .028 2.819 .010
均方和 自由度 均方 F统计量 显著性
MA·MA3与
平均点赞数
回归分析
回归 39138.341 1 39138.341 16.050 .001
残差 53647.400 22 2438.518
总体 92785.741 23
未标准化系数 标准误差 标准化系数 t统计量 显著性
MA·MA3 .373 .093 .649 4.006 .001
常数 -1036.985 313.440 -3.308 .003
表4  回归分析结果
图5  MA·MA3与密度和平均点赞数曲线拟合
检验统计量 1%评判值 5%评判值 10%评判值
MA·MA3 -0.66 -3.75 -3.00 -2.63
Z检验P值=0.86
Density -2.78
Z检验P值=0.06
Average Like -2.39
Z检验P值=0.15
表5  平稳性检验
滞后阶数 参数 对数似然函数 特征值 统计量 5%评判值
0 3 -41.42 . 37.98 29.68
1 8 -29.85 0.63 14.82* 15.41
2 11 -22.91 0.45 0.94 3.76
3 12 -22.44 0.04
表6  协整秩检验(样本: 2-24, 观测数=23)
方程 剔除 F统计量 自由度 P值
1 MA·MA3 Density .00 1 0.99
2 MA·MA3 Average Like 4.18 1 0.06*
3 MA·MA3 ALL 3.29 2 0.06*
4 Density MA·MA3 .00 1 0.95
5 Density Average Like 7.61 1 0.01**
6 Density ALL 4.96 2 0.02**
7 Average Like MA·MA3 1.92 1 0.18
8 Average Like Density 5.04 1 0.04**
9 Average Like ALL 3.58 2 0.05**
表7  格兰杰因果检验
[1] 刘力 . 行为金融理论对效率市场假说的挑战[J]. 经济科学, 1999(3):63-71.
( Liu Li . The Challenge of Behavior Economic Theory to Efficient Market Hypojournal[J]. Economic Science, 1999(3):63-71.
[2] Nofsinger J R . Social Mood and Financial Economics[J]. The Journal of Behavioral Finance, 2010,6(3):144-160.
doi: 10.1007/s11356-019-06686-7 pmid: 31836971
[3] Bollen J, Mao H, Zeng X . Twitter Mood Predicts the Stock Market[J]. Journal of Computational Science, 2011,2(1):1-8.
doi: 10.1016/j.jocs.2010.12.007
[4] Nofer M, Hinz O . Using Twitter to Predict the Stock Market Where is the Mood Effect?[J]. Business& Information Systems Engineering, 2015,57(4):229-242.
doi: 10.1016/j.scitotenv.2019.135995 pmid: 31841909
[5] See-To E W K, Yang Y . Market Sentiment Dispersion and Its Effects on Stock Return and Volatility[J]. Electronic Markets, 2017,27(3):283-296.
doi: 10.1007/s12525-017-0254-5
[6] 黄润鹏, 左文明, 毕凌燕 . 基于微博情绪信息的股票市场预测[J]. 管理工程学报, 2015,29(1):47-52, 215.
( Huang Runpeng, Zuo Wenming, Bi Lingyan . Predicting the Stock Market Based on Microblog Mood[J]. Journal of Industrial Engineering and Engineering Management, 2015,29(1):47-52, 215.)
[7] 程琬芸, 林杰 . 社交媒体的投资者涨跌情绪与证券市场指数[J]. 管理科学, 2013,26(5):111-119.
( Cheng Wanyun, Lin Jie . Investors’ Bullish Sentiment of Social Media and Stock Market Indices[J]. Journal of Management Science, 2013,26(5):111-119.)
[8] 赵明清, 武圣强 . 基于微博情感分析的股市加权预测方法研究[J]. 数据分析与知识发现, 2019,3(2):43-51.
( Zhao Mingqing, Wu Shengqiang . Research on Stock Market Weighted Prediction Method Based on Micro-Blog Sentiment Analysis[J]. Data Analysis and Knowledge Discovery, 2019,3(2):43-51.)
[9] Nassirtoussi A K, Aghabozorgi S, Wah T Y , et al. Text Mining for Market Prediction: A Systematic Review[J]. Expert Systems with Applications, 2014,41(16):7653-7670.
doi: 10.1016/j.eswa.2014.06.009
[10] Nguyen T H, Shirai K, Velcin J . Sentiment Analysis on Social Media for Stock Movement Prediction[J]. Expert Systems with Applications, 2015,42(24):9603-9611.
doi: 10.1016/j.eswa.2015.07.052
[11] 余传明, 龚雨田, 王峰 , 等. 基于文本价格融合模型的股票趋势预测[J]. 数据分析与知识发现, 2018,2(12):33-42.
( Yu Chuanming, Gong Yutian, Wang Feng , et al. Predicting Stock Prices with Text and Prices Combined Model[J]. Data Analysis and Knowledge Discovery, 2018,2(12):33-42.)
[12] Reed M . A Study of Social Network Effects on the Stock Market[J]. Journal of Behavioral Finance, 2016,17(4):342-351.
doi: 10.1371/journal.pone.0179479 pmid: 28658307
[13] 许启发, 伯仲璞, 蒋翠侠 . 基于分位数Granger因果的网络情绪与股市收益关系研究[J]. 管理科学, 2017,30(3):147-160.
( Xu Qifa, Bo Zhongpu, Jiang Cuixia . Exploring the Relationship Between Internet Sentiment and Stock Market Returns Based on Quantile Granger Causality Analysis[J]. Journal of Management Science, 2017,30(3):147-160.)
[14] Gálvez R H, Gravano A . Assessing the Usefulness of Online Message Board Mining in Automatic Stock Prediction Systems[J]. Journal of Computational Science, 2017,19:43-56.
doi: 10.1016/j.jocs.2017.01.001
[15] 丁慧, 吕长江, 黄海杰 . 社交媒体、投资者信息获取和解读能力与盈余预期——来自“上证e互动”平台的证据[J]. 经济研究, 2018,53(1):153-168.
( Ding Hui, Lv Changjiang, Huang Haijie.Social Media , Investor Sophistication and Earning Expectation: Evidence from SSE E-Interaction[J]. Economic Research Journal, 2018,53(1):153-168.)
[16] 丁慧, 吕长江, 陈运佳 . 投资者信息能力: 意见分歧与股价崩盘风险——来自社交媒体“上证e互动”的证据[J]. 管理世界, 2018,34(9):161-171.
( Ding Hui, Lv Changjiang, Chen Yunjia . Investor Information Ability: Opinion Division and Stock Market Crash Risk: Evidence from SSE E-Interaction[J]. Management World, 2018,34(9):161-171.)
[17] 孙书娜, 孙谦 . 投资者关注和股市表现——基于雪球关注度的研究[J]. 管理科学学报, 2018,21(6):60-71.
( Sun Shuna, Sun Qian . Investor Attention and Market Performance:Evidence Based on “Xueqiu Attention”[J]. Journal of Management Sciences in China, 2018,21(6):60-71.)
[18] 石勇, 唐静, 郭琨 . 社交媒体投资者关注、投资者情绪对中国股票市场的影响[J]. 中央财经大学学报, 2017(7):45-53.
( Shi Yong, Tang Jing, Guo Kun . The Study of Social Media Investor Attention and Sentiment’s Influence on Chinese Stock Market[J]. Journal of Central University of Finance & Economics, 2017(7):45-53.)
[19] Li B, Chan K C, Ou C , el al. Discovering Public Sentiment in Social Media for Predicting Stock Movement of Publicly Listed Companies[J]. Information Systems, 2017,69:81-92.
doi: 10.1016/j.is.2016.10.001
[20] He G, Zhu S Z, Gu H F . A PLS Approach to Measuring Investor Sentiment in Chinese Stock Marke[J]. Discrete Dynamics in Nature and Society, 2017: Article ID 2387543.
doi: 10.1155/2013/720818 pmid: 25083120
[21] Nguyen T H, Shiral K, Velcin J , et al. Sentiment Analysis on Social Media for Stock Movement Prediction[J]. Expert Systems with Applications, 2015,42(24):9603-9611.
doi: 10.1016/j.eswa.2015.07.052
[22] Patel J, Shah S, Thakkar P , et al. Predicting Stock and Stock Price Index Movement Using Trend Deterministic Data Preparation and Machine Learning Techniques[J]. Expert Systems with Applications, 2015,42(1):259-268.
doi: 10.1016/j.eswa.2014.07.040
[23] Patel J, Shah S, Thakkar P , et al. Predicting Stock Market Index Using Fusion of Machine Learning Techniques[J]. Expert Systems with Applications, 2015,42(4):2162-2172.
doi: 10.1016/j.eswa.2014.10.031
[24] Sun A, Lachanski M, Fabozzi F J . Trade the Tweet: Social Media Text Mining and Sparse Matrix Factorization for Stock Market Prediction[J]. International Review of Financial Analysis, 2016,48:272-281.
doi: 10.1016/j.irfa.2016.10.009
[25] Chen C, Wu D X, Hou C Y , et al. Exploiting Social Media for Stock Market Prediction with Factorization Machine [C]// Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technologies. 2014,2:142-149.
[26] 陈卫华, 徐国祥 . 基于深度学习和股票论坛数据的股市波动率预测精度研究[J]. 管理世界, 2018,34(1):180-181.
( Chen Weihua, Xu Guoxiang . Research on Prediction Accuracy of Stock Market Volatility Based on Deep Learning and Stock Forum Data[J]. Management World, 2018,34(1):180-181.)
[27] López-Cabarcos M A, Piñeiro-Chousa J, Pérez-Pico A M . The Impact Technical and Non-Technical Investors Have on the Stock Market: Evidence from the Sentiment Extracted from Social Networks[J]. Journal of Behavioral and Experimental Finance, 2017,15:15-20.
doi: 10.1016/j.jbef.2017.07.003
[28] 王聪, 柴时军, 田存志 , 等. 家庭社会网络与股市参与[J]. 世界经济, 2015,38(5):105-124.
( Wang Cong, Chai Shijun, Tian Cunzhi , et al. Home Social Networks and Stock Participation[J]. The Journal of World Economy, 2015,38(5):105-124.)
[29] 刘海飞, 许金涛, 柏巍 , 等. 社交网络、投资者关注与股价同步性[J]. 管理科学学报, 2017,20(2):53-62.
( Liu Haifei, Xu Jintao, Bai Wei , et al. Social Networks, Investor Attention and Stock Price Synchronicity[J]. Journal of Management Sciences in China, 2017,20(2):53-62.)
[30] Granger C W J . Investigating Causal Relations by Econometric Models and Cross-spectral Methods[J]. Econometrica, 1969,37(3):424-438.
doi: 10.2307/1912791
[31] 徐恪, 张赛, 陈昊 , 等. 在线社会网络的测量与分析[J]. 计算机学报, 2014,37(1):165-188.
( Xu Ke, Zhang Sai, Chen Hao , et al. Measurement and Analysis of Online Social Networks[J]. Chinese Journal of Computers, 2014,37(1):165-188.)
[32] Daniel K, Hirshleifer D, Subrahmanyam A . Investor Psychology and Security Market Under- and Overreactions[J]. The Journal of Finance, 1998,53(6):1839-1885.
doi: 10.1111/0022-1082.00077
[1] 安璐,梁艳平. 突发公共卫生事件微博话题与用户行为选择研究*[J]. 数据分析与知识发现, 2019, 3(4): 33-41.
[2] 席林娜,窦永香. 基于计划行为理论的微博用户转发行为影响因素研究*[J]. 数据分析与知识发现, 2019, 3(2): 13-20.
[3] 吴朋民,陈挺,王小梅. Altmetrics与引文指标相关性研究[J]. 数据分析与知识发现, 2018, 2(6): 58-69.
[4] 叶光辉,胡婧岚,徐健,夏立新. 社交博客标签增长态势与连接模式分析*[J]. 数据分析与知识发现, 2018, 2(6): 70-78.
[5] 陈芬,付希,何源,薛春香. 融合社会网络分析与影响力扩散模型的微博意见领袖发现研究*[J]. 数据分析与知识发现, 2018, 2(12): 60-67.
[6] 王忠义,张鹤铭,黄京,李春雅. 基于社会网络分析的网络问答社区知识传播研究[J]. 数据分析与知识发现, 2018, 2(11): 80-94.
[7] 李真,丁晟春,王楠. 网络舆情观点主题识别研究*[J]. 数据分析与知识发现, 2017, 1(8): 18-30.
[8] 李飞,张健,王宗水. 社会化推荐研究进展与发展趋势演化*——基于文献计量和社会网络分析的视角[J]. 数据分析与知识发现, 2017, 1(6): 22-35.
[9] 陈远,刘福珍,吴江. 基于二模复杂网络的共享经济平台用户交互行为研究*[J]. 数据分析与知识发现, 2017, 1(6): 72-82.
[10] 王晰巍,张柳,李师萌,王楠阿雪. 新媒体环境下社会公益网络舆情传播研究* ——以新浪微博“画出生命线”话题为例[J]. 数据分析与知识发现, 2017, 1(6): 93-101.
[11] 夏立新,杨金庆,程秀峰. 基于情境感知技术的移动数据自动采集系统设计与实现*[J]. 数据分析与知识发现, 2017, 1(5): 82-93.
[12] 范如霞,曾建勋,高亚瑞玺. 基于合作网络的学者动态学术影响力模式识别研究[J]. 数据分析与知识发现, 2017, 1(4): 30-37.
[13] 王曰芬,靳嘉林. 比较分析《现代图书情报技术》近10年发文特征与发展趋势*[J]. 现代图书情报技术, 2016, 32(9): 1-16.
[14] 王曰芬,贾新露,傅柱. 学术社交网络用户内容使用行为研究*——基于科学网热门博文的实证分析[J]. 现代图书情报技术, 2016, 32(6): 63-72.
[15] 张磊,马静,李丹丹,沈洋. 语义社会网络的超网络模型构建及关键节点自动化识别方法研究*[J]. 现代图书情报技术, 2016, 32(3): 8-17.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn