臺灣博碩士論文加值系統

影響股價變動之因素一直是研究學者長期關注之議題，然目前研究仍無法完全百分之百解釋股價變動之原因，這代表仍有些影響因素尚未被發現。本研究嘗試透過文字探勘技術，分析財經新聞內容中所隱含的資料是否為影響股價變動的因素之一。本研究設計兩種實驗模型，首先透過結巴字典加上自建詞典將財經新聞內容正確的斷詞後，利用詞頻（term frequency，簡稱TF）及詞頻反向文件頻率（term frequency-inverse document frequency，簡稱TF-IDF）演算法分別建構文字矩陣（document-term matrix，簡稱DTM），找出財經新聞當中的關鍵字及其重要性變數，最後加入三因子變數建構迴歸模型，來探討財經新聞與股價變動之間的關聯性，並分別從兩種模型得出財經新聞中對股價產生影響之關鍵字。

Factors that affect the fluctuations of the share price are the subject of the long-term research by scholars. However, recent studies can not be fully illustrated of that subject. This indicates that some factors have yet been discovered. This study attempts to analyze whether the information implied in the contents of the
financial news is one of the factors affecting the subject. Two experimental models are designed in this study. First of all, the contents of the financial news are correctly segmented through a JiebaR dictionary and a self-built dictionary. Secondly, the document-term matrix are set up respectively to find out the key words and the vital variables of the contents of the financial news by using the term frequency and the algorithm of the term frequency-inverse document frequency to set up respectively. Finally, the Fama-French 3-factor model is applied to construct a regression model in order to discuss the relevance between the contents of the financial news and the share price. This study derives the key words that affect the share price in the contents of the financial news from two models.

1.緒論 1
2.文獻回顧 4
3. 研究方法 7
3.1資料來源 7
3.2自建詞典及刪除停用詞 8
3.3 TF、TF-IDF演算法 8
3.4 文字矩陣 10
3.5 單根檢定 11
3.6 迴歸分析 12
4.實證分析 14
4.1實證過程 14
4.2 迴歸分析結果－TF 18
4.3 迴歸分析結果－TF-IDF 21
5.結論 24
參考文獻 26
附錄 28

1. 黃裕烈、管中閔（2017），「FOMC經濟使命與臺灣財經變數之關係：文字探勘的應用」，即將出版。
2. 鍾任明、李維平及吳澤民　（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》，10，1-30。
3. 顧廣平（2005），「單因子, 三因子或四因子模式?」，《證券市場發展季刊》17，101-146。
4. Armesto M. T., R. Hernández‐Murillo, M. T. Owyang and J. Piger（2009）, “Measuring the information content of the beige book: A mixed data sampling approach,” Journal of Money, Credit and Banking, 41, 35-55.
5. Berger H., J. De Haan and J. E. Sturm（2011）, “Does money matter in the ECB strategy? New evidence based on ECB communication,” International Journal of Finance and Economics, 16, 16-31.
6. Dickey D. A., and W. A. Fuller（1979）, “Distribution of the estimators for autoregressive time series with a unit root,” Journal of the American statistical association, 74, 427-431.
7. Doran J. S., D. R. Peterson and S. M. Price（2012）, “Earnings conference call content and stock price: the case of REITs,” The Journal of Real Estate Finance and Economics, 45, 402-434.
8. Granger C. W. and P. Newbold（1974）, “Spurious regressions in econometrics,” Journal of econometrics, 2, 111-120.
9. Hayo B. and M. Neuenkirch（2013）, “Do Federal Reserve presidents communicate with a regional bias?” Journal of Macroeconomics, 35, 62-72.
10. Hoberg G. and G. Phillips（2010）, “Product market synergies and competition in mergers and acquisitions: A text-based analysis,” Review of Financial Studies, 23, 3773-3811.
11. Loughran T., and B. McDonald（2011）, “When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks,”The Journal of Finance, 66, 35-65.
12. Loughran T., and B. McDonald（2014）, “Measuring readability in financial disclosures,”The Journal of Finance, 69（4）, 1643-1671.
13. Loughran T., and B. McDonald（2016）, “Textual analysis in accounting and finance: A survey,” Journal of Accounting Research, 54, 1187-1230.
14. Newey W. K. and K. D. West（1987）, “A simple, positive semi-definite, heteroskedasticity and autocorrelation consistent covariance matrix,” Econometrica, 55, 703–708.
15. Sadique S., F. In, M. Veeraraghavan and P. Wachtel（2013）, “Soft information and economic activity: Evidence from the Beige Book,” Journal of Macroeconomics, 37, 81-92.