基于金融微博情感与传播效果的股票价格预测

doi:10.6040/j.issn.1671-9352.1.2015.E26

摘要/Abstract

摘要： 目前对微博情绪与金融预测之间关系的研究多数停留于诸如模式识别、语义分析、情感挖掘等文本挖掘技术,而较少研究微博情感传递过程。以金融微博文本情感挖掘和语义分析为基础,对相关的股票价格曲线进行拟合预测分析,包括对微博信息转播模型的研究和对微博情绪预测模型的研究。首先通过分析微博转播过程中的多个因素,包括转发情绪吸收、微博内容影响力、微博作者影响力、微博发布时间等,对模型自身进行拟合效果优化。其次,针对认证和非认证用户分类分析,并加入了转发次数的对其的再度影响,发现不同类型不同转发的用户对于股市曲线的影响滞后期不同。最后,在针对股市曲线变化的不同时期,对模型的拟合效果进行分析。给定金融市场某一特定关键词,采集了500,000多条金融微博及其相关用户信息。实验结果表明,新集成模型表现强于简单神经网络模型,而且是否为认证用户以及微博转发次数对微博滞后期的影响有所不同。此外,新模型的拟合效果,在股市上升期模型的拟合效果最好,下降期次之,平稳振荡期效果最差。

关键词: 微博, 股票, 情感挖掘, 预测, 传播效果

Abstract: At present, there are many studies on the relationship between Weibo sentiment and financial forecast. Most forecasting studies concern excessively on text mining techniques, such as pattern recognition, semantic or sentiment analysis, but neglect the procedure of moods dissemination. We provide an integrated framework, including the semantic mining, information transmission and propagating factors analysis, to predict stock prices more accurately. First, we select several factors in the dissemination process, such as emotional absorption of forwarding, influence of content and poster, release time, etc. to optimize the fitting effect of original model. Second, we classify users into two categories, verified or unverified users. And we also take the count of forwarding into account, checking its effect on stock prices fluctuation. Third, we compare the fitting effect of prediction models for different periods of the stock curve. Given a certain keyword related to financial market, we collected over 500,000 Micro-blogs and their user information from Weibo. Experiments demonstrate that our proposed integrated framework outperformed the simple neural network method. We observe that user category and the count of forwarding differ on the lag phase of influence. And more, we found that the model fitting effect were the best in the rising periods of stock prices curves, the second place in the declining and the worst in the fluctuating.

Key words: sentiment mining, stock, Weibo, prediction, propagation effect

中图分类号:

TP391

朱梦珺,蒋洪迅,许伟. 基于金融微博情感与传播效果的股票价格预测[J]. 山东大学学报（理学版）, 2016, 51(11): 13-25.

ZHU Meng-jun,JIANG Hong-xun*,XU Wei. Weibo moods and propagation factors based stock prices prediction[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(11): 13-25.

参考文献

[1] JIANG Long, YU Mo, ZHOU Ming, et al. Target-dependent twitter sentiment classification[C] // Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2011, 1:151-160.
[2] GO A, BHAYANI R, HUANG Lei. Twitter sentiment classification using distant supervision[R]. Stanford: Stanford University, 2009.
[3] KONTOPOULOS E, BERBERIDIS C, DERGIADES T, et al. Ontology-based sentiment analysis of twitter posts[J].Expert Systems with Applications, 2013, 40(10):4065-4074.
[4] THELWALL M, BUCKLEY K, PALTOGLOU G. Sentiment in twitter events[J]. Journal of the American Society for Information Science and Technology, 2011, 62(2):406-418.
[5] READ J. Using emoticons to reduce dependency in machine learning techniques for sentiment classification[C/OL] //Proceedings of the ACL Student Research Workshop, Association for Computational Linguistics(2005), 2005: 43-48.[2015-03-08]. http://portal.acm.org/citation.cfm?id=1628969.
[6] DAVIDIV D, TSURO, RAPPOPORT A. Enhanced sentiment learning using twitter hashtags and smileys[C/OL].Coling 2010. [2015-02-16]. http://dl.acm.org/ft_-gateway.cfm?id=1944594& type=pdf.
[7] SAIF H, HE Y, ALANI H. Alleviating data sparsity for twitter sentiment analysis[C/OL].Proceedings of the 2nd Workshop on Making Sense of Microposts(#MSM2012).[2015-02-06]. http://ceur-ws.org/Vol-838/paper_-01.pdf.
[8] 刘志明, 刘鲁. 基于机器学习的中文微博情感分类实证研究[J]. 计算机工程与应用, 2012, 48(1):1-4. LIU Zhiming, LIU Lu. Empirical study of sentiment classification for Chinese Microblog based on machine learning[J]. Computer Engineering and Applications, 2012, 48(1):1-4.
[9] 谢丽星,周明,孙茂松. 基于层次结构的多策略中文微博情感分析和特征抽取[J]. 中文信息学报,2012, 26(1):73-83. XIE Lixing, ZHOU Ming, SUN Maosong. Hierarchical structure based hybrid approach to sentiment analysis of Chinese Microblog and its feature extraction[J]. Journal of Chinese Information Processing, 2012, 26(1):73-83.
[10] 林江豪,阳爱民,周咏梅,等. 一种基于朴素贝叶斯的微博情感分类研究[J]. 计算机工程与科学,2012,34(9):160-165. LIN Jianghao, YANG Aimin, ZHOU Yongmei, et al. Classification of Microblog sentiment based on naive Bayesian[J]. Computer Engineering & Science, 2012, 34(9):160-165.
[11] JANSEN B J, ZHANG M, SOBEL K, et al. Micro-blogging as online word of mouth branding[C] //Proceedings of the 27th International Conference Extended Abstracts on Human Factors in Computing System. New York: ACM, 2009:3859-3864.
[12] BOYD D, GOLDER S, LOTAN G. Tweet, tweet, retweet: conversational aspects of retweeting on twitter[C] //Proceedings of the 43rd Hawaii International Conference on System Sciences. Los Alamitos: IEEE Computer Society, New York: ACM, 2010:1567-1666.
[13] SUH B, HONG L, PIROLLI P, et al. Want to be retweeted? large scale analytics on factors impacting retweet in twitter network[C] //Proceedings of IEEE 2nd International Conference on Social Computing(Social Com). Washington: IEEE Computer Society, 2010:177-184.
[14] 夏雨禾. 微博互动的结构与机制—基于对新浪微博的实证研究[J]. 新闻传播与研究, 2010(4):60-69. XIA Yuhe. The structure and mechanism of Micro-blog interaction: an empirical study on Sina Microblog[J]. Journalism & Communication, 2010(4):60-69.
[15] 李英乐. 微博传播效果预测技术研究[D].郑州:解放军信息工程大学, 2013. LI Yingle. Research on the prediction technology of micro-blog communication effect [D]. Zhengzhou:The PLA Information Engineering University, 2013.
[16] 张旸,路荣,杨青. 微博客中转发行为的预测研究[J]. 中文信息学报,2012, 26(4):109-114, 121. ZHANG Yang, LU Rong, YANG Qing. Predicting retweeting in Microblogs[J]. Journal of Chinese Information Processing, 2012, 26(4):109-114, 121.
[17] ZHANG Xue, FUEHRES H, GLOOR P A, et al. Predictiong stock market indicators through twitter “I hope it is not as bad as I fear”[J]. Procedia-Social and Behavioral Sciences, 2011, 26(26):55-62.
[18] BOLLEN J, MAO Huina, ZENG Xiaojun. Twitter mood predicts the stock market [J]. Journal of Computational Science, 2011, 2(1):1-8.
[19] 金桃,岳敏,穆进超,等. 基于SVM的多变量股市时间序列预测研究[J]. 计算机应用与软件,2010,27(6):191-194,209. JIN Tao, YUE Min, MU Jinchao, et al. On SVM-based multi-variable stock market time series prediction[J]. Computer Applications & Software, 2010, 27(6):191-194,209.
[20] 王超,李楠,李欣丽,等. 倾向性分析用于金融市场波动率的研究[J]. 中文信息学报,2009,23(1):95-99. WANG Chao, LI Nan, LI Xinli, et al. The research on financial volatility with sentiment analysis[J]. Journal of Chinese Information Processing, 2009, 23(1):95-99.
[21] 余佩琨,钟瑞军. 个人投资者情绪能预测市场收益率吗?[J]. 南开管理评论,2009,12(1):96-101. YU Peikun, ZHONG Ruijun. Can individual investor sentiment predict market returns?[J]. Nankai Business Review, 2009, 12(1):96-101.
[22] 饶育蕾,刘达锋. 行为金融学[M].上海:上海财经大学出版社, 2003. RAO Yulei, LIU Dafeng. Behavioral finance [M].Shanghai: Shanghai University of Finance and Economics Press, 2003.

相关文章 15

[1]	罗艾珂,喻召杰. 基于联合学习的电力安全实体抽取及风险预测方法[J]. 《山东大学学报(理学版)》, 2026, 61(5): 27-37.
[2]	张鲁宁,王景升. 基于自适应残差动态融合图注意力网络的交通速度预测[J]. 《山东大学学报(理学版)》, 2026, 61(5): 90-101.
[3]	余雷,孙懿,华金铭,李腊全. 基于深度神经网络的重症监护室脓毒症患者死亡风险预测模型分析[J]. 《山东大学学报(理学版)》, 2026, 61(1): 26-35.
[4]	严莉,呼海林,王高洲,张闻彬,潘法定,张啸,郑艳伟. 基于长短时序预测的拓扑构建与控制[J]. 《山东大学学报(理学版)》, 2025, 60(9): 41-51.
[5]	施虹艺,马周明. 多尺度决策系统的覆盖粗糙模糊集及其最优尺度选择[J]. 《山东大学学报(理学版)》, 2024, 59(5): 114-130.
[6]	郭战胜,常丽荣,陈雯静,侯旭光,施坤涛. 海黍子不同生长部位附生菌群结构比较[J]. 《山东大学学报(理学版)》, 2024, 59(11): 31-39.
[7]	吴贤君,唐绍诗,王明秋. 融合基础属性和通信行为的移动用户个性化推荐[J]. 《山东大学学报(理学版)》, 2023, 58(9): 81-93.
[8]	王新乐,杨文峰,廖华明,王永庆,刘悦,俞晓明,程学旗. 基于多维度特征的主题标签流行度预测[J]. 《山东大学学报(理学版)》, 2020, 55(1): 94-101.
[9]	王文卿,撖奥洋,于立涛,张智晟. 自编码器与PSOA-CNN结合的短期负荷预测模型[J]. 《山东大学学报(理学版)》, 2019, 54(7): 50-56.
[10]	王培名,陈兴蜀,王海舟,王文贤. 多策略融合的微博数据获取技术研究[J]. 《山东大学学报(理学版)》, 2019, 54(5): 28-36, 43.
[11]	张帆,罗成,刘奕群,张敏,马少平. 异质搜索环境下的用户偏好性预测方法研究[J]. 山东大学学报（理学版）, 2017, 52(9): 26-34.
[12]	张聪,裴家欢,黄锴宇,黄德根,殷章志. 基于语义图优化算法的中文微博观点摘要研究[J]. 山东大学学报（理学版）, 2017, 52(7): 59-65.
[13]	张中军,张文娟,于来行,李润川. 基于网络距离和内容相似度的微博社交网络社区划分方法[J]. 山东大学学报（理学版）, 2017, 52(7): 97-103.
[14]	许忠好,李天奇. 基于复杂网络的中国股票市场统计特征分析[J]. 山东大学学报（理学版）, 2017, 52(5): 41-48.
[15]	胡默之,姚天昉. 中文微博观点句识别及评价对象抽取方法[J]. 山东大学学报（理学版）, 2016, 51(7): 81-89.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed