臺灣博碩士論文加值系統

本研究分析台灣股票市場即時新聞揭露、日內報酬及波動度之間的關聯性，藉由蒐集個股日內價格與相關之新聞揭露，檢視在不同的市場趨勢、產業特性與個股走勢等狀態下，開盤前或盤中是否有新聞揭露，對於個股盤中報酬與波動度之影響。本研究將新聞揭露狀態區分為四種情形，包括開盤前及盤中皆沒有新聞、開盤前沒新聞盤中有新聞、開盤前有新聞盤中沒新聞和開盤前與盤中皆有新聞，統計四種新聞揭露分類下之新聞量、公司家數及平均報酬。與先前研究之差異在於，本研究除了蒐集個股盤中揭露的新聞量之外，亦延伸Demers and Vega (2011)之研究，將即時新聞量化成可衡量的資訊並建立新聞淨樂觀指標，捕捉每一則新聞反映出來的樂悲觀程度。實證結果顯示，台灣證券市場平均每一天有近八成的上市公司沒有在新聞報紙上曝光，換言之，新聞報導上僅揭露約兩成上市公司的相關報導；就個股平均的報酬分析可發現，盤中有即時新聞揭露的公司，其平均的日報酬高於盤中沒有新聞的公司，此發現在不同產業分類下亦得到一致的結論，此外新聞的淨樂觀程度越高時其平均的報酬越高。本研究證實，新聞媒體在盤中交易時段內對個股揭露的相關報導，確實會對個股的報酬與波動產生衝擊。

We examine the relationship between news releases, intraday returns and volatility in Taiwan stock market. The high-frequency five-minute intraday price and trading volume of each stock are employed. We would investigate the impact of media news to the return and volatility of each stock and the news released during or prior to the trading session is classified. The research design includes the different market trend, feature of industries, and conditions of each stock. Our study would separate the news releases into four conditions, including whether the news releases in the session and before the market open. The differences between this paper and previous studies lie in that the comprehensive intraday price and Chinese news of each stock are collected and the analysis of linguistic text mining is applied to extract the information content of Chinese news. Proxy variables of the news effect are measured by the news sentiment (SR) by referring to Vega (2006) and Demers and Vega (2011). The empirical results show that there is no report in newspaper for approximately 80% corporations in Taiwan stock markets. The stock returns with real-time news in the session are better than the returns without real-times news in the session. After incorporating the categorization of different industries, the results are consistent. Besides, the higher of the news sentiment, the higher of average returns. The news released in the session influences the stock returns and realized volatility.

目錄
誌謝 II
摘要 III
英文摘要 IV
目錄 V
圖目錄 VI
表目錄 VII
壹、緒論 2
貳、文獻探討 4
一、新聞與股票報酬之間的關係 4
二、文辭探勘在財務領域之應用與相關研究 5
參、資料與研究設計 7
一、資料來源及樣本期間 7
二、新聞情緒淨樂觀指標 7
三、報酬、累積報酬與真實波動度 8
四、日內分時資料之變數說明 9
五、不同新聞揭露狀態下之研究設計 11
六、產業分類下之研究設計 12
七、迴歸分析之研究設計 14
八、小結 15
肆、實證分析 16
一、日內分時資料統計 16
二、相關係數分析 19
三、敘述性統計量 23
四、新聞揭露之平均狀況 25
五、新聞揭露狀況與大盤之趨勢分析 26
六、不同市場狀態下新聞揭露與報酬之分析 31
七、不同市場狀態下新聞揭露與真實波動度之分析 33
八、區分產業下新聞揭露型態與報酬之分析 35
九、區分產業下新聞揭露型態與波動度之分析 37
十、迴歸分析 38
伍、結論 44
參考文獻 46

參考文獻
巫育琦，2011，「資訊不對稱是否影響媒體報導與股票報酬間關係之探討」，碩士論文，國立台北大學企業管理學系。
林柏宇，2008，「使用角色分類結合文字探勘技術建立股市預測模型」，碩士論文，中原大學資訊管理研究所。
林逸偉，2011，「公開資訊及私有資訊於證券異常報酬預警、波動度預測與投資組合應用」，碩士論文，銘傳大學財務金融研究所。
林裕晟，2009，「考慮景氣循環趨勢應用資料探勘於企業財務危機預測」，碩士論文，國立高雄大學資訊管理研究所。
陳俊達，王台帄，劉昭麟，2007，「以文件分類技術預測股價趨勢」，第十九屆自然語言與語音處理研討會論文集，頁 347-361。
馮雅民，2006，「運用文件探勘技術進行新聞報導評價分類－以網路財經新聞為例」，碩士論文，樹德科技大學資訊管理研究所。
廖婉茹，2011，「公開新聞資訊內涵是否能增進臺灣企業信用風險指標之預測能力?」，碩士論文，銘傳大學財務金融研究所。
鍾任明、李維帄、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，頁 1-30。
Abad, D., Sanabria, S., and Yagu‥e, J., 2008, “Strategic timing of annual earnings announcements: Evidence from an order-driven market,” Review of Quantitative Finance Accounting 32, 287-308.
Andersen, T. G., Bollerslev, T., Diebold, F. X., and Vega, C., 2003, “Real-time price discovery in stock, bond and foreign exchange markets,” Journal of International Economics 73, 251-277.
Andersen, T. G., & Bollerslev, T., 1998, “Answering the skeptics: Yes, standard volatility models do provide accurate forecasts,” International Economic Review 39, 885-906.
Barclay, M. J., and Hendershott, T., 2003, “Price discovery and trading after hours,” Review of Financial Studies Winter 16, 1041-1073.
Cao, C., Ghysels, E., and Hateway, F., 2000, “Price discovery without trading: Evidence from the Nasdaq preopening,” Journal of Finance 3, 1339-1365.
Chan, W. S., 2003, “Stock price reaction to news and no-news: Drift and reversal after headlines,” Journal of Financial Economics 70, 223-260.
Chang, S. C., Sheng-Syan, C., Robi, K. C., and Yueh-Hsiang, L., 2008, “Weather and intraday patterns in stock returns and trading activity,” Journal of Banking & Finance 32, 1754-1766.
Yu-Lun, C., and Yin-Feng, G., 2010, “News announcements and price discovery in foreign exchange spot and futures markets,” Journal of Banking & Finance 34, 1628-1636.
Demers, E. A., and Vega, C., 2011, “Linguistic tone in earnings announcements: News or noise?” Working Paper.
Dorre, J., Gerstl, P., and Seiffert, R., 1999, “Text mining: Finding nuggets in mountains of textual data,” Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 398-401.
Engelberg, J. E., and Christopher, A. P., 2011, “The Causal Impact of Media in Financial Markets,” Journal of Finance, 67-97.
Feldman, R., and Dagan, I., 1995, “Knowledge discovery in textual database (KDT),” Proceedings of the first ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 112-117.
Frakes, W. B., and Baeza-Yates, R., 1992, “Information retrieval: Data structures and algorithms,” Prentice-Hall.
Fuertes, A. M., Kalotychou, E., and Todorovic, N., 2009, “Intraday price and volume information for volatility-based trading: Does it pay?” Working Paper.
Gros-Klusmann, A., and Hautsch, N., 2009, “Quantifying high-frequency market reactions to real-time news sentiment announcements,” Working Paper.
Hanousek, J., and Kočenda, E., 2009, “Intraday price discovery in emerging European stock markets,” Working Paper.
Hirshleifer, D., 2001, “Investor psychology and asset pricing,” Journal of Finance 56, 1533-1597.
 
Lo, A. W., and Repin, D. V., 2002, “The psychophysiology of real-time financial risk processing,” Journal of Cognitive Neuroscience 14, 323-339.
Nie, J., Briscobis, M., and Ren, X., 1996, “On Chinese text retrieval,” Conference Proceedings of SIGIR, 225-233.
Pritamani, M., and Vijay, S., 2001, “Return predictability following large price changes and information releases,” Journal of Banking & Finance 25, 631-656.
Schwert, G. W., 1989, “Why does stock market volatility change over time?” Journal of Finance 94, 28-66.
Sprenger, T. O., and Welpe, I. M., 2011, “News or noise? The stock market reaction to different types of company-specific news events,” Working Paper.
Sullivan, D., 2001. “Document warehousing and text mining,” Wiley Computer Publishing.
Tetlock, P. C., 2007, “Giving content to investor sentiment: The role of media in the stock market,” Journal of Finance 62, 1139-1168.
Tetlock, P. C., Saar-Tsechansky, M., and Macskassy, S., 2008, “More than words: Quantifying language to measure firms’ fundamentals,” Journal of Finance 63, 1437-1467.
Vega, C., 2006, “Stock price reaction to public and private information,” Journal of Financial Economics 82, 103-133.
Wei, Y. C., 2011, “The information content of Chinese news sentiment around earnings announcements,” Working Paper.
Wright, W. F., and Bower, G. H., 1992, “Mood effects on subjective probability assessment,” Organizational Behavior and Human Decision Process 52, 276-291.