异质性财经新闻与股市关系研究*

doi:10.11925/infotech.2096-3467.2020.0063

数据分析与知识发现

2021, Vol. 5

Issue (1): 99-111 https://doi.org/10.11925/infotech.2096-3467.2020.0063

研究论文｜

本期目录 | 过刊浏览 | 高级检索

异质性财经新闻与股市关系研究*

吕华揆^1,²(

),刘政昊^1,²,钱宇星¹,洪旭东³

¹武汉大学信息资源研究中心武汉 430072
²武汉大学大数据研究院武汉 430072
³上海财经大学财经研究所上海 200433

Relationship Between Financial News and Stock Market Fluctuations

Lv Huakui^1,²(

),Liu Zhenghao^1,²,Qian Yuxing¹,Hong Xudong³

¹Center for Studies of Information Resources, Wuhan University, Wuhan 430072, China
²Big Data Institute, Wuhan University, Wuhan 430072, China
³Institute of Finance and Economics, Shanghai University of Finance and Economics,Shanghai 200433, China

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF (5095 KB) HTML ( 20 )
输出: BibTeX | EndNote (RIS)

摘要

【目的】 对财经新闻进行分类,探讨不同类型财经新闻与股市之间的关系。【方法】 运用Word2Vec+k-Means方法对新闻文本进行聚类,并运用VAR模型从时间维度分析不同类别新闻如何影响股市以及股市的变动如何反作用于新闻。【结果】 不同类别下的新闻情绪效应与信息效应能够显著影响股市成交量、振幅与收益,但对股市影响侧重不同;股市收益率与成交量分别反作用于新闻情感分歧与新闻长度,但依旧受新闻类别的影响。【局限】 从股市整体角度分析股市与新闻之间的关系,而未考虑个股间差异。【结论】 新闻与股市之间存在相互影响机制,且存在时间滞后效应;新闻类别是二者相互影响的关键变量。

	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
	吕华揆
	刘政昊
	钱宇星
	洪旭东

关键词 ：异质性新闻, VAR模型, 股票市场, 情感分析

Abstract：

[Objective] This paper explores the impacts of financial news on the stock market fluctuations.[Methods] We used the method of “Word2Vec+k-means” to cluster news texts, and utilized VAR model to analyze the relationship between different types of news and the stock market performance.[Results] The sentiments and information of news significantly affect the trading volumes, amplitudes and returns of the stock market. Meanwhile, the fluctuations of stock market also influenced the emotion and length of the news reports.[Limitations] We did not analyze the relationship between the individual stock and news reports.[Conclusions] There are interactions and time-lag effects between news and stock market, while the news category is a key player.

Key words： Heterogeneous News VAR Model Stock Market Sentiment Analysis

收稿日期: 2020-01-19 出版日期: 2021-02-05

ZTFLH:

F832

基金资助:*本文系国家自然科学基金重大研究计划的研究成果之一项目编号(91646206)

通讯作者: 吕华揆 E-mail: lvhuakui@whu.edu.cn

引用本文:

吕华揆,刘政昊,钱宇星,洪旭东. 异质性财经新闻与股市关系研究*[J]. 数据分析与知识发现, 2021, 5(1): 99-111.
Lv Huakui,Liu Zhenghao,Qian Yuxing,Hong Xudong. Relationship Between Financial News and Stock Market Fluctuations. Data Analysis and Knowledge Discovery, 2021, 5(1): 99-111.

链接本文:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2020.0063 或 https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2021/V5/I1/99

Fig.1 研究框架

Table 1 三类新闻的定义

指标	公式	变量解释
收益率^[29]	$Retur n t = ln (Pric e t) - ln (Pric e t - 1)$	$Pric e t 为$ 沪深300在t时刻的收盘价 $; Pric e t - 1$ 为t时刻前一时刻的收盘价
成交量	$TradingVolum e t = ln (Round (Trading V t, - 2))$	$Trading V t$ 为t时刻的成交量;Round()函数表示对成交量取整
股市振幅	$Amplitud e t = Pric e t h - Pric e t l Pric e t l$	$Pric e t h$ 为t时刻沪深300的最高价 $; Pric e t l$ 为t时刻的最低价
新闻情感^[29]	$Sen t k = ln [1 + M k pos 1 + M k neg]$ $Sen t t = 1 j ∑ k = 1 j Sen t k$	$Sen t k$ 为每条新闻情感值 $; M k pos$ 为文本k中所含积极情感得分,即文本中所有积极情感句分值之和; $M k neg$ 为消极情感得分; $Sen t t$ 为t时刻的新闻情感值;j为t时刻的新闻数量
情感分歧^[30]	$SentS V t = 1 j ∑ k = 1 j (Sen t t, k - Sen t t) 2$	$Sen t t, k$ 为t时刻新闻k表达的情感; $Sen t t$ 为t时刻平均文本情感值
新闻数量^[31]	$NewsVolum e t = ln (1 + News V t)$	$News V t 为$ 当天的新闻数量
新闻长度^[32,33]	$NewsLengt h t = ln ∑ k = 1 j NewsLengt h k j$	$NewsLengt h k$ 为文本k所含字数

Table 2 指标定义

Table 3 三类新闻描述性统计

Fig.2 股市波动类新闻对股市的影响

Fig.3 股权及高管变动类新闻对股市的影响

Fig.4 战略及其他类新闻对股市的影响

Fig.5 股市对股市波动类新闻的影响

Fig.6 股市对股权及高管变动类新闻的影响

[1]	中国证券登记结算有限责任公司. 投资者统计[DB/OL]. http://www.chinaclear.cn/zdjs/tjyb2/center_tjbg.shtml .
[1]	(China Securities Depository and Clearing Corporation Limited. Investor Statistics[DB/OL]. http://www.chinaclear.cn/zdjs/tjyb2/center_tjbg.shtml
[2]	陈健, 曾世强 . 投资者情绪对股票价格波动的影响研究[J]. 价格理论与实践, 2018(7):99-102.
[2]	( Chen Jian, Zeng Shiqiang . Research on the Influence of Investor Sentiment on Stock Price Volatility, Price: Theory & Practice, 2018(7):99-102.)
[3]	Deng S, Huang Z J, Sinha A P , et al. The Interaction Between Microblog Sentiment and Stock Return: An Empirical Examination[J]. MIS Quarterly, 2018,42(3):895-918.
[4]	杨继东 . 媒体影响了投资者行为吗?——基于文献的一个思考[J]. 金融研究, 2007(11):93-102.
[4]	( Yang Jidong . Does the Media Influence Investor Behavior? -A Reflection Based on Literature, Journal of Financial Research, 2007(11):93-102.)
[5]	倪浩 . 新闻信息对不同类型投资者行为的影响[D]. 天津:天津大学, 2017.
[5]	( Ni Hao . The Impact of News Information on the Behavior of Different Types of Investors[D]. Tianjin: Tianjin University, 2017.)
[6]	Williams P, Aaker J L . Can Mixed Emotions Peacefully Coexist?[J]. Journal of Consumer Research, 2002,28(4):636-649. doi: 10.1086/jcr.2002.28.issue-4
[7]	程萧潇 . 场景效应还是内容效应?——财经新闻、网络舆情对股市行情的实证检验[J]. 统计与信息论坛, 2019,34(7):69-75.
[7]	( Cheng Xiaoxiao . Contextual Effect or Content Effect? Empirical Test of Financial News and Online Public Opinion on Stock Market Quotation[J]. Statistics & Information Forum, 2019,34(7):69-75.)
[8]	尹海员 . 新闻媒体报道对投资者情绪影响效应研究——来自我国股票市场的经验证据[J]. 厦门大学学报(哲学社会科学版), 2016(2):92-101.
[8]	( Yin Haiyuan . A Study on Effect of Media Reports on Investor Sentiment: Evidence from China’s Stock Market[J]. Journal of Xiamen University (Arts & Social Sciences), 2016 ( 2):92-101.)
[9]	史峰 . 金融媒体新闻情绪及其对股市影响研究[D]. 北京:对外经济贸易大学, 2018.
[9]	( Shi Feng . Research on Financial News Sentiment and Its Impact on Stock Market[D]. Beijing: University of International Business and Economics, 2018.)
[10]	Li Q, Wang J, Bao L. Media Tone, Bias, and Stock Price Crash Risk: Evidence from China[J]. Asia-Pacific Journal of Accounting & Economics, DOI: 10.1080/16081625. 2019.1654396.
[11]	Chan W S . Stock Price Reaction to News and No-News: Drift and Reversal After Headlines[J]. Journal of Financial Economics, 2003,70(2):223-260.
[12]	Kelly S, Ahmad K . Estimating the Impact of Domain-Specific News Sentiment on Financial Assets[J]. Knowledge-Based Systems, 2018,150:116-126.
[13]	Mitchell M L, Mulherin J H . The Impact of Public Information on the Stock Market[J]. The Journal of Finance, 1994,49(3):923-950.
[14]	Fang L, Peress J . Media Coverage and the Cross‐Section of Stock Returns[J]. The Journal of Finance, 2009,64(5):2023-2052.
[15]	饶育蕾, 彭叠峰, 成大超 . 媒体注意力会引起股票的异常收益吗?——来自中国股票市场的经验证据[J]. 系统工程理论与实践, 2010,30(2):287-297.
[15]	( Rao Yulei, Peng Diefeng, Cheng Dachao . Does Media Attention Cause Abnormal Return? —Evidence from China’s Stock Market[J]. Systems Engineering-Theory & Practice, 2010,30(2):287-297.)
[16]	杨阳 . 上市公司新闻情感倾向对股价的影响分析[D]. 北京:北京理工大学, 2015.
[16]	( Yang Yang . Analysis on the Impact of the Sentiment of Firm-Apecific News on Stock Price[D]. Beijing: Beijing Institute of Technology, 2015.)
[17]	Boudoukh J, Feldman R, Kogan S , et al. Information, Trading, and Volatility: Evidence from Firm-Specific News[J]. The Review of Financial Studies, 2019,32(3):992-1033.
[18]	Li Q, Wang T J, Li P , et al. The Effect of News and Public Mood on Stock Movements[J]. Information Sciences, 2014,278:826-840.
[19]	刘海飞, 许金涛 . 互联网异质性财经新闻对股市的影响——来自中国互联网数据与上市公司的证据[J]. 产业经济研究, 2017(1):76-88.
[19]	( Liu Haifei, Xu Jintao . The Impact of Internet Heterogeneous Financial and Economic News on Stock Market: Evidence from Chinese Internet Data and Listed Companies, Industrial Economics Research, 2017(1):76-88.)
[20]	钟惠波, 沈依琴, 曾奕萌 . 新闻话语方式对股价的影响——基于财经媒体类型的视角[J]. 北京理工大学学报(社会科学版), 2018,20(3):98-104.
[20]	( Zhong Huibo, Shen Yiqin, Zeng Yimeng . The Influence of News Discourse and Stock Price——Based on the Perspective of Financial Media Types[J]. Journal of Beijing Institute of Technology(Social Sciences Edition), 2018,20(3):98-104.)
[21]	Sims C A . Macroeconomics and Reality[J]. Econometrica, Econometric Society, 1980,48(1):1-48.
[22]	Dewan S, Ramaprasad J. Social Media, Traditional Media, Music Sales[J]. MIS Quarterly, 2014,38(1):101-122.
[23]	Li D F, Wang Y T, Madden A , et al. Analyzing Stock Market Trends Using Social Media User Moods and Social Influence[J]. Journal of the Association for Information Science and Technology, 2019,70(9):1000-1013.
[24]	Tetlock P C . Giving Content to Investor Sentiment: The Role of Media in the Stock Market[J]. The Journal of Finance, 2007,62(3):1139-1168.
[25]	朱南丽, 邹平, 张永平 , 等. 基于博客/微博信息量的投资者关注度测量研究——来自中国股票市场的经验数据[J]. 经济问题探索, 2015(2):159-166.
[25]	( Zhu Nanli, Zou Ping, Zhang Yongping , et al. Research on Investor’s Attention Measurement Based on Blog/Microblog Information Volume——Empirical Data from China’s Stock Market, Inquiry into Economic Issues, 2015(2):159-166.)
[26]	徐琳宏, 林鸿飞, 潘宇 , 等. 情感词汇本体的构造[J]. 情报学报, 2008,27(2):180-185.
[26]	( Xu Linhong, Lin Hongfei, Pan Yu , et al. Constructing the Affective Lexicon Ontology[J]. Journal of the China Society for Scientific and Technical Information, 2008,27(2):180-185.)
[27]	Bian S B, Jia D K, Li F , et al. A New Chinese Financial Sentiment Dictionary for Textual Analysis in Accounting and Finance[J]. SSRN Electronic Journal, 2019. DOI: 10.2139/ssrn.3446388.
[28]	陈晓东 . 基于情感词典的中文微博情感倾向分析研究[D]. 武汉:华中科技大学, 2012.
[28]	( Chen Xiaodong . Research on Sentiment Dictionary Based Emotional Tendency Analysis of Chinese Microblog[D]. Wuhan: Huazhong University of Science and Technology, 2012.)
[29]	Sun Y, Liu X, Chen G Y , et al. How Mood Affects the Stock Market: Empirical Evidence from Microblogs[J]. Information & Management, 2020,57(5):103181.
[30]	岑咏华, 谭志浩, 吴承尧 . 财经媒介信息对股票市场的影响研究:基于情感分析的实证[J]. 数据分析与知识发现, 2019,3(9):98-114.
[30]	( Cen Yonghua, Tan Zhihao, Wu Chengyao . Impacts of Financial Media Information on Stock Market: An Empirical Study of Sentiment Analysis[J]. Data Analysis and Knowledge Discovery, 2019,3(9):98-114.)
[31]	Li T, van Dalen J, van Rees P J . More than Just Noise? Examining the Information Content of Stock Microblogs on Financial Markets[J]. Journal of Information Technology, 2018,33(1):50-69. doi: 10.1057/s41265-016-0034-2
[32]	Li F. Annual Report Readability, Current Earnings, Earnings Persistence[J]. Journal of Accounting and Economics, 2008,45(2-3):221-247. doi: 10.1016/j.jacceco.2008.02.003
[33]	Lawrence A . Individual Investors and Financial Disclosure[J]. Journal of Accounting and Economics, 2013,56(1):130-147. doi: 10.1016/j.jacceco.2013.05.001
[34]	武慧锋 . 新闻报道对股票价格影响的实证研究[J]. 财政科学, 2017,21(9):135-140.
[34]	( Wu Huifeng . Empirical Study on How News Impact Stock Prices[J]. Fiscal Science, 2017,21(9):135-140.)

[1]	钟佳娃,刘巍,王思丽,杨恒. 文本情感分析方法及应用综述^*[J]. 数据分析与知识发现, 2021, 5(6): 1-13.
[2]	刘彤,刘琛,倪维健. 多层次数据增强的半监督中文情感分析方法^*[J]. 数据分析与知识发现, 2021, 5(5): 51-58.
[3]	王雨竹,谢珺,陈波,续欣莹. 基于跨模态上下文感知注意力的多模态情感分析 ^*[J]. 数据分析与知识发现, 2021, 5(4): 49-59.
[4]	常城扬,王晓东,张胜磊. 基于深度学习方法对特定群体推特的动态政治情感极性分析^*[J]. 数据分析与知识发现, 2021, 5(3): 121-131.
[5]	张梦瑶, 朱广丽, 张顺香, 张标. 基于情感分析的微博热点话题用户群体划分模型 ^*[J]. 数据分析与知识发现, 2021, 5(2): 43-49.
[6]	韩普, 张伟, 张展鹏, 王宇欣, 方浩宇. 基于特征融合和多通道的突发公共卫生事件微博情感分析^*[J]. 数据分析与知识发现, 2021, 5(11): 68-79.
[7]	徐红霞,于倩倩,钱力. 基于主题模型和情感分析的话题交互数据观点对抗性分析 ^*[J]. 数据分析与知识发现, 2020, 4(7): 110-117.
[8]	姜霖,张麒麟. 基于引文细粒度情感量化的学术评价研究*[J]. 数据分析与知识发现, 2020, 4(6): 129-138.
[9]	石磊,王毅,成颖,魏瑞斌. 自然语言处理中的注意力机制研究综述^*[J]. 数据分析与知识发现, 2020, 4(5): 1-14.
[10]	李铁军,颜端武,杨雄飞. 基于情感加权关联规则的微博推荐研究*[J]. 数据分析与知识发现, 2020, 4(4): 27-33.
[11]	沈卓,李艳. 基于PreLM-FT细粒度情感分析的餐饮业用户评论挖掘[J]. 数据分析与知识发现, 2020, 4(4): 63-71.
[12]	薛福亮,刘丽芳. 一种基于CRF与ATAE-LSTM的细粒度情感分析方法^*[J]. 数据分析与知识发现, 2020, 4(2/3): 207-213.
[13]	张翼鹏,马敬东. 突发公共卫生事件误导信息受众情感分析及传播特征研究^*[J]. 数据分析与知识发现, 2020, 4(12): 45-54.
[14]	谭荧,张进,夏立新. 社交媒体情境下的情感分析研究综述[J]. 数据分析与知识发现, 2020, 4(1): 1-11.
[15]	聂卉,何欢. 引入词向量的隐性特征识别研究*[J]. 数据分析与知识发现, 2020, 4(1): 99-110.

Viewed

Full text

Abstract

Cited

Shared

Discussed