摘要
随着互联网的广泛普及,网络成为信息传播的主要渠道。在金融领域,网络信息对股票市场的影响日益显现,投资者愈加依赖网络信息进行投资决策。股票论坛成为投资者交流与讨论的重要场所,也是信息、内幕、传闻等股票消息集中的平台,论坛中的在线股票评论信息已成为影响用户态度和投资决策的重要因素,认识其对股票市场的影响受到日益关注。
在我国,股票市场处于新兴发展阶段,非理性投资者居多,投资决策更易受消息与传闻的影响,因此研究我国股票论坛中在线股评的影响是合理且具有重要意义的,但目前对我国股票论坛的信息价值还缺乏必要的认识与研究,本文正是针对这一点,对该研究方向进行了初步探讨,为我国股票市场研究提供新的视角。
本文基于行为金融理论,认为非理性投资者的心理与行为影响金融市场,对我国在线股票评论活动展开了分析,主要研究了在线股评与股票市场表现的关系。本文应用文本分类技术提取了在线股评内容中的投资者情感倾向,并结合评论发表数量,从股市整体、单只股票、通讯行业三个角度研究了在线股评的影响。研究表明,在线股评包含有价值信息,整体上在线评论因素与股市交易量更相关,评论数量与投资者态度对单只股票的超额收益具有解释能力。通讯行业截面数据分析显示,在线股评数量对股票收益、涨跌额、交易量的差异存在影响。
With the widespread of the Internet, the network became the main channel for dissemination of information. The internet is clearly playing an ever increasing role in financial, investors increasingly rely on web information to make investment decisions. Stock forum which is full of stock information, insider and rumors is an important communication platform for investors to discuss, activities on forum has an important impact on users’attitudes and decisions. Understand and exploring its impact on the stock market is growing concern and hot topics.
In China, The stock market has just started. The majority of non-rational investors are more vulnerable to be affected by the news and rumors, so study the impact of activities on China's stock forum is reasonable and important. However, researchers are lack of understanding of the value information in the stock forum. To address this point, this paper discusses the stock forum and proposes a new perspective for China's stock research.
Based on behavioral finance theory which suggests the psychology and behavior of the irrational investors affect financial markets, this work study investors activities on China's stock forum and explores the relationship between stock market activities and the online stock reviews. In this paper, text classification technique is used to extract the sentiments expressed by users in reviews. Combined with the reviews volume, the impact of reviews on the whole stock market, individual stock and telecommunications industry is measured. Results show that the online reviews factors and trading volume is more relevant. The reviews volume and sentiment has explanatory power for excess return of individual stock. Cross-sectional analysis suggests reviews volume has impact on returns, change amount and trading volume.
引文
[1] Shleifer A. Inefficient Markets: An Introduction to Behavioral Finance[M]. Oxford University Press, USA, 2000:52.
[2] Shleifer A, Summers L H. The Noise Trader Approach to Finance[J]. The Journal of Economic Perspectives. 1990, 4(2): 19-33.
[3]第27次中国互联网络发展状况统计报告[R].中国互联网信息中心, 2011.
[4] Chen P Y, Wu S, Yoon J. The Impact of Online Recommendations and Consumer Feedback on Sales[J]. ICIS 2004 Proceedings. 2004: 58.
[5] Clemons E K, Gao G G, Hitt L M. When Online Reviews Meet Hyperdifferentiation: A Study of the Craft Beer Industry[J]. Journal of Management Information Systems. 2006, 23(2): 149-171.
[6] Godes D, Mayzlin D. Using Online Conversations to Study Word-of-Mouth Communication[J]. Marketing Science. 2004: 545-560.
[7] Liu Y. Word of Mouth for Movies: Its Dynamics and Impact on Box Office Revenue[J]. Journal of Marketing. 2006, 70(3): 74-89.
[8] Ye Q, Law R, Gu B. The Impact of Online User Reviews on Hotel Room Sales[J]. International Journal of Hospitality Management. 2009, 28(1): 180-182.
[9] Zhang Z, Ye Q, Law R, et al. The Impact of E-Word-Of-Mouth on the Online Popularity of Restaurants: A Comparison of Consumer Reviews and Editor Reviews[J]. International Journal of Hospitality Management. 2010, 29(4): 694-700.
[10] Brown G W, Cliff M T. Investor Sentiment and the Near-Term Stock Market[J]. Journal of Empirical Finance. 2004, 11(1): 1-27.
[11] De Long J B, Shleifer A, Summers L H, et al. Noise Trader Risk in Financial Markets[J]. Journal of Political Economy. 1990, 98(4): 703-738.
[12] Chopra N, Lee C, Shleifer A, et al. Yes, Discounts on Closed-End Funds Are A Sentiment Index[J]. Journal of Finance. 1993, 48(2): 801-808.
[13] Elton E J, Gruber M J, Busse J A. Do Investors Care about Sentiment?[J].Journal of Business. 1998, 71(4): 477-500.
[14] Lakonishok J, Maberly E. The Weekend Effect: Trading Patterns of Individual and Institutional Investors[J]. Journal of Finance. 1990, 45(1): 231-243.
[15] Abraham A, Ikenberry D L. The Individual Investor and the Weekend Effect[J]. Journal of Financial and Quantitative Analysis. 1994, 29(02): 263-277.
[16] Saunders Jr E M. Stock Prices and Wall Street Weather[J]. The American Economic Review. 1993, 83(5): 1337-1345.
[17] Kamstra M J, Kramer L A, Levi M D. Losing Sleep At the Market: The Daylight Saving Anomaly[J]. American Economic Review. 2000, 90(4): 1005-1011.
[18] Hirshleifer D, Shumway T. Good Day Sunshine: Stock Returns and the Weather[J]. The Journal of Finance. 2003, 58(3): 1009-1032.
[19] Neal R, Wheatley S M. Do Measures of Investor Sentiment Predict Returns?[J]. Journal of Financial and Quantitative Analysis. 1998, 33(04): 523-547.
[20] Fisher K L, Statman M. Investor Sentiment and Stock Returns[J]. Financial Analysts Journal. 2000, 56(2): 16-23.
[21] Baker M, Wurgler J. Investor Sentiment and the Cross-Section of Stock Returns[J]. The Journal of Finance. 2006, 61(4): 1645-1680.
[22] Zhang Y, Swanson P E. Are Day Traders Bias Free? Evidence from Internet Stock Message Boards[J]. Journal of Economics and Finance. 2010, 34(1): 96-112.
[23] Sabherwal S, Sarkar S K, Zhang Y. Online Talk: Does It Matter?[J]. Managerial Finance. 2008, 34(6): 423-436.
[24] Koski J L, Rice E M, Tarhouni A. Noise Trading and Volatility: Evidence from Day Trading and Message Boards[J]. University of Washington. 2004.
[25] Antweiler W, Frank M. Internet Stock Message Boards and Stock Returns[J]. University of British Columbia Working Paper. 2002.
[26] Wysocki P D. Private Information, Earnings Announcements and Trading Volume, or Stock Chat on the Internet. A Public Debate about Private Information[J]. Working Paper, University of Michigan Business School. 2000, 1001: 41234-48109.
[27] Sehgal V, Song C. SOPS: Stock Prediction Using Web Sentiment[C]. Seventh IEEE International Conference on Data Mining: IEEE, 2007.
[28] Das S R, Chen M Y. Yahoo! For Amazon: Sentiment Extraction from Small Talk on the Web[J]. Management Science. 2007, 53(9): 1375-1388.
[29] Wysocki P D. Cheap Talk on the Web: the Determinants of Postings on Stock Message Boards[J]. Working Paper, Univercity of Michigan. 1998.
[30] Tumarkin R, Whitelaw R F. News or Noise? Internet Postings and Stock Prices[J]. Financial Analysts Journal. 2001, 57(3): 41-51.
[31] Antweiler W, Frank M Z. Is All That Talk Just Noise? The Information Content of Internet Stock Message Boards[J]. Journal of Finance. 2004, 59(3): 1259-1294.
[32] Das S, Martinez-Jerez A, Tufano P. Einformation: A Clinical Study of Investor Discussion and Sentiment[J]. Financial Management. 2005, 34(3): 103-137.
[33] Zimbra D, Fu T, Li X. Assessing Public Opinions through Web 2.0: A Case Study on Wal-Mart[J]. The 13th International Conference on Information Systems. 2009.
[34] Gu B, Konana P, Liu A, et al. Identifying Information in Stock Message Boards and Its Implications for Stock Market Efficiency[Z]. Evanston, Illinois: Workshop on Information Systems and Economics, 2006.
[35] Fama E F. Efficient Capital Markets: A Review of Theory and Empirical Work[J]. The Journal of Finance. 1970, 25(2): 383-417.
[36] Fama E F. The Behavior of Stock-Market Prices[J]. The Journal of Business. 1965, 38(1): 34-105.
[37]谭加劲.资本市场有效理论的演变和发展[J].金融教学与研究. 2002(001): 41-44.
[38] Thaler R H. Advances in Behavioral Finance[M]. Russell Sage Foundation Publications, 1993.
[39] Lintner G. Behavioral Finance: Why Investors Make Bad Decisions[J]. The Planner. 1998, 13(1): 7-8.
[40] Hsee C K. Myopic Maximization: Medium Effect in Decision-Making[J]. Working Paper, Graduate School of Business, University of Chicago. 2000.
[41]刘超.基于行为金融学的中国证券分析师行为研究[D].天津:天津大学博士学位论文, 2006:22-23.
[42]侯红卫,李雪峰.基于行为金融理论的投资者行为研究方法现状与展望[J].科学决策. 2010(002): 83-93.
[43]李心丹.行为金融理论:研究体系及展望[J].金融研究. 2005(001): 175-190.
[44]刘志阳.国外行为金融理论述评[J].经济学动态. 2002(003): 71-75.
[45]邹莉娜,赵梅链.行为金融理论的发展及评述[J].经济师. 2006(005): 250-251.
[46] Black F. Noise[J]. Journal of Finance. 1986, 41(3): 529-543.
[47] Froot K A, Scharfstein D S, Stein J C. Herd on the Street: Informational Inefficiencies in A Market with Short-Term Speculation[J]. National Bureau of Economic Research Cambridge, Mass. USA. 1990.
[48]董大勇.投资者参与股票论坛的影响因素[J].系统工程. 2011(01): 51-56.
[49] Feldman R, Dagan I. Knowledge Discovery in Textual Databases (KDT)[C]. Proceedings of the First International Conference on Knowledge Discovery and Data Mining (KDD-95): 1995.
[50] Tan A H. Text Mining: The State of the Art and the Challenges[C]. Proceedings of the PAKDD, Workshop on Knowledge Disocovery from Advanced Databases: Citeseer, 1999.
[51]李淑英,杜丽娟.浅谈文本分类技术[J].中国科技博览. 2009(012): 244.
[52]袁军鹏,朱东华,李毅.文本挖掘技术研究进展[J].计算机应用研究. 2006, 2: 1-4.
[53]张启宇,朱玲,张雅萍.中文分词算法研究综述[J].情报探索. 2008(011): 53-56.
[54]李凡,鲁明羽.关于文本特征抽取新方法的研究[J].清华大学学报:自然科学版. 2001, 41(007): 98-101.
[55]薛为民,陆玉昌.文本挖掘技术研究[J].北京联合大学学报(自然科学版). 2005, 19(4): 59-63.
[56]唐焕玲,孙建涛,陆玉昌.文本分类中结合评估函数的TEF-WA权值调整技术[J].计算机研究与发展. 2005, 42(001): 47-53.
[57]卢苇,彭雅.几种常用文本分类算法性能比较与分析[J].湖南大学学报:自然科学版. 2007, 34(006): 67-69.
[58]刘怀亮,张治国,马志辉,等.基于SVM与KNN的中文文本分类比较实证研究[J].情报理论与实践. 2008(006):941-944.
[59] Cortes C, Vapnik V. Support-Vector Networks[J]. Machine Learning. 1995, 20(3): 273-297.
[60] Vapnik V N. An Overview of Statistical Learning Theory[J]. IEEE Transactions on Neural Networks. 1999, 10(5): 988-999.
[61]张鹏招.基于X~ 2统计的中文文本分类特征选择方法研究[D].重庆:重庆大学硕士学位论文, 2008:19.
[62] Sebastiani F. Machine Learning in Automated Text Categorization[J]. ACM computing surveys (CSUR). 2002, 34(1): 1-47.
[63]卢琦泽,叶德谦,南敏.基于遗传算法和神经网络的股票价格预测[J].电脑开发与应用. 2010, 23(002): 61-62.
[64]晏艳阳,胡俊.股票价格与上市公司业绩的关联分析――对中国证券市场的研究[J].系统工程. 2006, 24(008): 63-69.
[65] Fung G, Yu J, Lam W. News Sensitive Stock Trend Prediction[J]. Advances in Knowledge Discovery and Data Mining. 2002: 481-493.
[66] Mittermayer M A. Forecasting Intraday Stock Price Trends with Text Mining Techniques[C]. Proceedings of the 37th Annual Hawaii International Conference on System Sciences: IEEE, 2004.
[67] Schumaker R P, Chen H. Textual Analysis of Stock Market Prediction Using Financial News[C]. Americas Conference on Information Systems (AMCIS): Citeseer, 2006.
[68] 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.
[69] Devitt A, Ahmad K. Sentiment Polarity Identification in Financial News: A Cohesion-Based Approach[C]. Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics: 2007.
[70]汉语分词系统官网. http://ictclas.org/.2010.
[71]陆觉民,马国栋,郑宇.基于数据挖掘技术的图书馆流通数据的关联分析[J].现代情报. 2009, 29(009): 108-110.
[72]史美景.会计信息对股票价格影响作用的回归分析[J].西部论坛. 2002, 4(002): 30-32.