本研究旨在探討網路情緒聲量與股價漲跌趨勢之互動關係，透過質化研究的觀察方式，找出一些足以預測股市波動的指標，以做為未來投資方向的參考依據。本研究係以2014年10月到2015年3月間之台指MSCI101上市公司為樣本，運用蜘蛛爬文技術取得網路上針對該企業討論的正面情緒聲量，如：快樂、看好、利多、成長、有感、推薦等..與負面情緒聲量，如：悲傷、低劣、看壞、下滑、生氣、落寞等，進行聲量統計，計算當正面情緒大於負面情緒時，與前日、當日、次1日、次2日、次3日、次4日、次5日股價上漲是否有關連，以及當負面情緒大於正面情緒時，與前日、當日、次1日、次2日、次3日、次4日、次5日股價下跌是否有關聯。
本研究主要實證結果如下：1. 當網路討論正面情緒大於負面情緒達51以上時，開始觀察到聲量發生的前或中或後，發生股票收盤價上漲的機率普遍大於總上漲的機率。2. 當網路討論負面情緒大於正面情緒達時，多數可觀察到前或當交易日下跌的機率大於總下跌的機率。3. 當網路討論正面情緒大於負面情緒達101以上時，普遍會發生當日甚至到次五交易日股價上漲機率大於總上漲的機率，情緒聲量此時可視為股價上漲的領先指標。但，當網路討論負面情緒大於正面情緒時，普遍會發生情緒聲量的前一天發生股票下跌機率大於總下跌的機率，情緒聲量此時可視為股價下跌的落後指標。但，各現象的發生仍依各企業特性與產業環境有所不同，情緒聲量與股價漲跌之間的影響關係也有所不同。
透過實證結果，網路情緒討論聲量與股價漲跌趨勢確實存在一定的互動關聯性。與Stockfeel曾提出運用社群網站Twitter上大眾情緒的推文可有效預測股票市場的發展趨勢不謀而合。

The purpose of this study is to discuss the relation between word of mouse and stock price fluctuations by analyzing the big data, then find out some indications that influence the stock market. This research chose the Taiwan MSCI 101 listed companies as samples during the period from October 2014 to March 2015. I used the spider-crawling-text technology to collect the positive words about those companies such as happy, optimistic, profitable, good, recommended and the negative words such as sadness, poor, bad, down, angry, lonely... After that I used those data to observe whether the stock prices are growing on previous day, current day, day1, day2, day3, day4 to day5 when the positive emotions were greater than the negative emotions, and vice versa.
The empirical results of this study are as follows: 1. When the positive emotions are greater than the negative emotions with difference up to 51 or more, it will affect investors’ decision from the previous day to the day after. The influence will depend on each company’s situation. 2. When the negative emotions are greater than the positive emotions, it often has the stock price declined from the previous day. The influence will depend on each company’s situation. 3. When the positive emotions are greater than the negative emotions with the difference up to 101 or more, it often impacts the stock price from the day to the following five days. At this case, the word of mouse can be regarded as a leading indicator of rising stock prices. However, when the negative emotions are greater than positive emotions, it often happens with the stock price declining on the previous day. At this case, the word of mouse can be regarded as a lagged indicator. However, no matter the influence or the indicator type are always depended on the situations.
Through these empirical results, we know that the stock prices fluctuation will be affected by the word of mouse. And it’s on the same wavelength with Stockfeel, which has proposed that we can predict the stock market trends by observing the public sentiment via Twitter Tweets.

中文部分
Jeanne W. Ross, Cynthia M. Beath & Anne Quaadgras(2013)。誰需要巨量資料。哈佛商業評論中文版。96-104。
MIC(2013)，巨量資料市場趨勢與商機，MIC，台北。
Thomas H. Davenport(2013)。巨量資料分析3.0版。哈佛商業評論。69-76。
李依蓉(2007)。文字探勘結合引文連結技術建構知識來源地圖之研究。銘傳大學資訊管理學系未出版碩士論文，台北。
卓越投資理財專欄。2013。 要知市場有多害怕 需認識『恐慌指數』 Pp1-2。
周賓鳳、池祥萱、周冠男、龔怡霖。2002。行為財務學：文獻回顧與展望。證券市場發展季刊。第二期，Pp1-47。
周賢榮(民86)。台灣股票市場價格行為之實證研究。行政院國家科學偉璇會專題研究計畫成果報告。國立台灣工業技術學員企業管理技術系。新竹。
林文盟(94)。關聯分析再台灣股市消息面與技術面分析之比較研究。中華大學資訊管理學系碩士論文。台北。
林意仁(2011)。網路群眾文化及其民主意涵-以Ptt Gossiping為例。國立政治大學社會學研究所碩士論文，台北。
林鈺靜(民104)，台灣股票市場各類別投資人從眾行為。國立台灣科技大學。民103年。台北。
施喻繻(2015)。運用文字探勘技術探討公開資訊內容、股價報酬率和專業機構投資人交易行為之關聯性：以台灣電子業上市公司為例。國立台灣科技大學企業管理系碩士論文，台北。
胡湘湘(2014)。IBM軟體事業處總經理賈景光。大數據藏金礦 銀行業挖商機。台灣銀行家。
張文君(民103)。負面網路口碑失效因素之探討以企業回應為觀點。國立台灣科技大學財金所碩士論文。台北。
陳士偉(99)。 探討股價股利宣告之超額報酬受投資人情緒影響之研究。國立台灣科技大學財金所碩士論文。台北。
陳咨博(2014)。公開資訊內容、股價報酬率與專業機構投資人交易行為之關聯性研究：以台灣股票市場為例。國立台灣科技大學企業管理系碩士論文，台北。
曾郁文(2012)。網路論壇中的第三人效果之研究 以批踢踢八卦版為例。國立中山大學傳播管理學系碩士論文。高雄。
黃彥聖(民82)。我國股市漲跌幅限制與股價變化關係之研究。行政院國家科學委員會專題研究計畫成果報告。國立台灣工業技術學員企業管理技術系。新竹。
葉乃嘉(2014)。巨量資料導入雲端服務關鍵技術議題探討。工研院IEK產業情報。新竹。
詹家昌，許月瑜，陳麗如(2015)。以媒體效果探討股市過度反應現象。交大學報，Vol. 35 No.1, 2015, pp. 47-72。
資訊研究團隊(2015)。巨量資料分析應用與產品發展趨勢剖析。資策會產業情報研究所。台北。
趙祖佑(2015)。巨量資料與物聯網引領產業新競局。工研院IEK產業情報。新竹。
薛怡青(2015,172期)。Big Data。天下雜誌。
謝雨珊(2014)。Big Data分析於醫療健康照護之應用。拓樸產研。台北。
魏伊伶(2013)。挑戰「大數據」-雲端應用與資料中心回顧與展望。工研院IEK產業情報。新竹。
鐘任明、李維平、吳澤民(2007)。運用文字探勘於日內股價漲跌趨勢預測之研究。中華管理評論國際學報，第十卷，第一期。
鐘尚倫(2008)。新聞資訊與股票市場動態之關聯性-報紙資訊對法人持股以及各股報酬率的影響。國立台灣大學碩士學位論文，台北。
鐘朝宏(1992)，投資學，國立編譯館，初版。
英文部分
Banerjee, A. (1992). A simple model of herd behavior. Quarterly Journal of Economics, 107(3), pp 797-818.
Bikhchandani, S. & Sharma, S. (2000). “Herd behavior in financial markets”. IMF Working Paper, March, 279.
Birz, G., & Lott, J. R. (2011). The effect of macroeconomic news on stock returns: New evidence from newspaper coverage. Journal of Banking & Finance, 35(11), pp 2791-2800.
Blume, Lawrence, Easley, D & O’Hara (1994). Market statistics and technical analysis: The role of volume, Journal of Finance 49, pp 153-181
Brown, S. & J. Warner (1985). Using Daily Stock Returns: The Case of Event Studies. Journal of Financial Economics, Vol. 14, pp. 3-32.
Brown, W. & M. Cliff (2004). Investor Sentiment and the Near-term Stock Market. Journal of Empirical Finance 11, pp. 1-27.
Burton G. Malkiel. Journal of Economic Perspectives (Winter 2003). Volume 17, Number 1, 59-82.
Busse, J.A, & Green, T. C. (2002). Market efficiency in real time. Journal of Financial Economics, 65(3), pp 415-437
Chang Liu, Chi Yang, Xuyun Zhang, Jinjun Chen (2014). Future Generation Computer Systems 49 (2015) pp 58–67
Conard, Jennifer, S, Hameed, A & Niden, C (1994). Volume and autocovariances in short-horizon individual security returns. Journal of Finance 49, pp 1305-1330
Coyne, K. R., & Witter, J. W. (2002). Taking the mystery out of investor behavior. Harvard Business Review. 80(9), 68-78.
Datar, V, Naik, N & Radcliffe, R (1998). Liquidity and assets returns: An alternative test, Journal of Finance Markets. 1, pp 203-220
De Bondt, Werner F. M., & Richard Thaler (1985). Does the stock market overreaction? .The Journal of Finance Vol, XL. No.3 July 1985.pp.793-808.
Eugene F. Fama(1965). The Behavior of Stock Market Price. Journal of Business. 38, Journal, pp 34-105.
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), pp 383-417.
Gidofalvi, G., & Elkan, C (2001). Using news articles to predict stock price movements, Department of Computer Science and Engineering: University of California, San Diego
Graham, J. R., (1999). Herding among investment newsletters: Theory and evidence, The Journal of Finance, Vol. 54. Iss.1, pp.237-269
Gurau, C. (2008). Integrated Online Marketing Communication: Implementation and Management. Journal of Communication Management, 12 (2), pp 169-184.
Hirshleifer, D., Lim, S. S., & Tech, S. H. (2009). Driven to distraction: Extraneous events and underreaction to earnings news. The Journal of Finance, 64(5), pp 2289-2325
Hong, Kubik, & Solomon (2000). Security analysts’career concerns and herding of earning forecasts. The Rand Journal of Economics, Vol. 31, Iss.1, pp.121-144.
Jegadeesh, N., & Titamn, S 1993. Returns to buying winners and selling losers: Implications for stock market efficiency. Journal of Finance 48, pp 65-91.
Kandel, E., & Pearson, N. D. (1995). Differential intepretation of public signals and trade in speculative markets, Journal of Political Economy, pp 831-872.
Karpof(1987), Campbell, J. Grossman ,S & Wang, J(1993). Trading volume and serial correlation in stock return Quarterly Journal of Economics, 107, pp 905-939
Kim, O., & Verrecchia, R. E. (1997). Pre-announcement and event-period private information. Journal of accounting and economics, 24(3), pp 395-419
Korpela & Tuominen (1997). Group decision support for analyzing logistics development projects, in: Proceedings of the 13th Hawaii International Conference, vol. 3, pp.493-502
Kozinets, Robert V. (2002). Utopian Consumption. Advances in Consumer Research, 29(1), 62-64.
Lee, Y., C. Jiang, & D. Indro (2002). Stock Market Volatility, Excess Returns, and the Role of Investor Sentiment. Journal of Banking &Finance, pp.2277-2299.
Maheswaran, Durairaj & Joan Meyers-Levy (1990). The influence of message framing and issue involvement. Journal of Marketing Research, 27 (3), pp 361-67
Mahoney, W. F.(1991). Investor Relations: The Professional’s Guide to Financial Marketing and Communications. NYIF Corp.
Malkiel, B. G. & E. F. Fama (1970). Efficient Capital Markets: A Review Of Theory And Empirical Work. The Journal of Finance 25(2): pp 383-417.
Osborne, M.F.M (1959). Brownian Motion in the Stock Market, Operation Research, Vol.7, pp. 145-173
Parka, Cheol & Thae Min Lee (2009). Information direction, website reputation and eWOM effect: A moderating role of product type, Journal of Busiiness Research, 62(1), pp 61-67
Sankaraguruswamy, S., Shen, J., & Yamada, T. (2006). Impact of firm-specific public information on the relation between prices and trading. Paper presented at the EFA 2006 Zurich Meetings.
Ying, C.C.(1996),”Stock Market Prices and Volume of Sales”, Econometrica, 4, 76-686.
網路資料
http://www.dcn.com.tw/invest/html/MSCI_02.htm
http://www.nielsen.com/tw/zh/press-room/2013/newsTWTrustInAd20130917.html
Stockfeel網站：http://www.stockfeel.com.tw/%E8%AE%93%E8%8F%AF%E7%88%BE%E8%A1%97%E4%B9%9F%E5%AE%B3%E6%80%95%E7%9A%84%E5%A4%A7%E6%95%B8%E6%93%9A%E5%88%86%E6%9E%90%E6%B5%AA%E6%BD%AE/