臺灣博碩士論文加值系統

臺灣投資環境特殊，臺灣股票市場存在漲跌幅限制以及非理性投資者造成投機行為導致無法立即反映過往的資訊，造成無效率市場。依據效率市場假說描述，假設理性投資者在投資環境下達到效率市場，仍無法獲得超額報酬。僅管如此仍有多位研究者從不同角度預測臺灣股市，其中包含了股市預測不同的理論與觀點以及方法。但是股市對於投資者而言期望能夠精準預測股票市場態勢，獲得合理的投資報酬。然而以往預測方法使得投資者不易探究，故本研究目的嘗詴建立『財經新聞探勘預測模式』，幫助投資者預先瞭解股票市場態勢。由於臺灣電子指數與臺灣股票市場連動性非常強烈，可得知研究臺灣股票市場新聞語料即可。藉此採用文字探勘可找出潛在新聞語料資訊，透過機器學習方式反應人類對於新聞的理解，藉以預測臺灣電子指數。實驗結果發現，財經新聞語料與當前股票市場走勢相符，很有可能市場波動造就財經新聞內容趨勢。不論之間交互影響為何，市場供給需求法則仍主導臺灣股票市場波動。

Taiwan investment environment is special, Taiwan stock market has the rise and decline limit as well as the non-rational investor causes the congenial behavior to cause to be unable to reflect immediately the passing information creates the inefficiency market. Describes based on the efficiency market hypothesis, the supposition rational investor issues the efficiency market in the investment environment, was still unable to obtain the exceeding the quota reward. Only managed so still had many researchers to forecast Taiwan stock market from the different angle, contained the stock market to forecast the different theory and the viewpoint as well as the method. But the stock market the expectation speaking of the investor to be able to the accurate forecast Stock market situation, obtains the reasonable investment reward. However formerly the forecast technique caused the investor not to be easy to inquire into, therefore this research goal attempt establishment 'the finance and economics news exploration forecast pattern', helps the investor to understand the stock market situation in advance. Because Taiwan electron index and Taiwan Capitalization Weighted Index is intense, may know that studies Taiwan Stock market news language materials then. Takes advantage of this uses the writing exploration to be possible to discover the latent news language materials information, responds the humanity by the machine learning way regarding the news understanding, so as to forecasts Taiwan electron index. The experimental result discovered that the finance and economics news language materials and the current stock market trend match case, has the possibility market fluctuation accomplishment finance and economics news content tendency very much. No matter between the interactions why, the market supplies demand principle still did lead Taiwan stock market fluctuation.

第一章 緒論 .......................................................................... 1
第一節 研究背景 ....................................................................... 1
第二節 研究動機 ....................................................................... 2
第三節 研究目的 ....................................................................... 4
第四節 研究問題 ....................................................................... 5
第五節 研究架構 ....................................................................... 6
第二章 文獻探討 ....................................................................... 7
第一節 預測方法 ....................................................................... 7
第二節 財經新聞 ...................................................................... 21
第三節 文字探勘 ...................................................................... 23
第三章 研究方法 ...................................................................... 27
第一節 研究程序 ...................................................................... 27
第二節 文件來源 ...................................................................... 35
第三節 系統建置 ...................................................................... 41
第四節 系統環境 ...................................................................... 45
第四章 實驗結果 ...................................................................... 47
第一節 信度分析 ...................................................................... 48
第二節 潛在語意索引字詞 ............................................................... 49
第三節 潛在語意索引-代表性字詞 ......................................................... 51
第四節 預測分析 ..................................................................... 57
第五章 結論 ........................................................................ 58

一、 中文部分
王名帆、洪志洋 (2010)。總體經濟因素與企業資本結構關聯性之研究—台灣上市電子公司為例。國立交通大學科技管理研究所，新竹市。
王雅玲、余尚武 (2010)。運用灰色系統理論於台灣上市公司財務比率變數之預測—以電子業為例。國立臺灣科技大學，臺北市。
呂玉銘、陳安斌 (1993)。運用類神經網路於臺灣證券市場基本面分析。國立交通大學資訊管理研究所，新竹市。
杜金龍(2008)：最新技術指標在臺灣股市應用的訣竅。台北市：財信出版有限公司。
吳佳龍、許光華、李見發 (2010)。臺灣股票市場技術分析獲利能力—以KD及MACD為例。朝陽科技大學財務金融所，台中市。
呂靜芬、馬黛 (2010)。法人交易行為和技術分析互動影響之探討。國立中山大學財務管理研究所，高雄市。
余鐵英、王昭文、吳訂宜(2007)。台股之弱式效率市場檢定。高苑學報‧第十三卷(2007/7)第191~220頁。
姜佩瑜、李宏志(2010)。外資交易行為是否誤導散戶投資行為下單?。國立政治大學財務管理研究所，臺北市。
張志向、謝松霖 (2005)。台灣股市漲跌幅限制之績效：價格發現與基本面價值。國立高雄大學金融管理系，高雄市。
黃之怡、羅文輝 (2009)。財經新聞可信度及對投資決策之影響研究。國立政治大學傳播學院碩士在職專班，臺北市。
黃婉君、李俊德 (2009)。比較ANFIS與類神經網路結合技術指標應用於股市預測之能力。大葉大學資訊管理所，彰化縣。
葉恆芬、劉駿州 (2000)。網路媒體可信度及其影響因素初探研究-以台灣地區網路使用者為例。國立中正大學電訊傳播研究所，嘉義 縣。
簡郁琳、沈慧聲 (2004)。媒介可信度之評估研究—以網路新聞為例。中國文化大學新聞研究所，臺北市。

二、 英文部份
Abbasi, A., & Chen, H. (2006). Visualizing Authorship for Identification. Intelligence and Security Informatics, 3975, 60-71. Springer.
Chen, K. J. & Kiu, S. H. (1992). Word Identification for Mandarin Chinese Sentences. Fifth International Conference on Computational Linguistics, pp. 101-107.
Yang, C. C., & Chung, A. (2002). A Personal Agent for Chinese Financial News on the Web. Journal of the American Society for Information Science and Technology, 53(2).
Duncan, J. (2000). Java API for XML Parsing. Development.
Erhardt, R. A.-A., Schneider, R., & Blaschke, C. (2006). Status of text-mining techniques applied to biomedical text. Drug Discovery Today, 11(7-8), 315-325.
Fama, E. F. (1965). The behavior of stock market prices. J Business, 38(1), 34-105.
Fama, E. F. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. Journal of Finance, 25(2), 383-417.
Chang, F., Dean, J., Ghemawat, S., Hsieh, W. C., Wallach, D. A., Burrows, M., Chandra, T., et al. (2006). Bigtable: A distributed storage system for structured data. Proceedings of the 7th USENIX Symposium on Operating Systems Design and Implementation OSDI’06, 26(2), 205-218.
Gidófalvi, G., & Elkan, C. (2001). Using news articles to predict stock price movements. Department of Computer Science and Engineering University of California San Diego.
Pui, G., Fung, C., Yu, J. X., & Lu, H. (2005). The Predicting Power of Textual Information on Financial Markets. IEEE Intelligent Informatics Bulletin, 5(1), 1-10.
Kim, J., & Choi, K. (2007). Patent document categorization based on semantic structural information. Information Processing & Management, 43(5), 1200-1215.
Landauer, T. K., Foltz, P. W., & Laham, D. (1998). An introduction to latent semantic analysis. Discourse Processes, 25(2), 259-284.
Mittermayer, M. A. (2004). Forecasting intraday stock price trends with text mining techniques. 37th Annual Hawaii International Conference on System Sciences 2004 Proceedings of the, 00(C), 64-73.
Mittermayer, M.-A., & Knolmayer, G. F. (2006). Text Mining Systems for Market Response to News: A Survey. Information Systems Journal, 41(184), 571-579. University of Bern.
Schumaker, R. P., & Chen, H. (2009). A quantitative stock prediction system based on financial news. Information Processing & Management, 45(5), 571-583.
Feldman, R., & Sanger, J. (2007). The Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data. Imagine (Vol. 34, p. 410). Cambridge University Press.
Chowdhury, G. (2004). Introduction to modern information retrieval. Introduction to Information Retrieval (Vol. 35, p. 496). Facet Publishing. Retrieved from http://strathprints.strath.ac.uk/2621/
Ong, T.-H., Chen, H., Sung, W.-K., & Zhu, B. (2005). Newsmap: a knowledge map for online news. Decision Support Systems, 39(4), 583-597.
Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. NY Springer (Vol. 8, p. 188). Springer.
EL-Manzalawy, Y., & Honavar, V. (2005). WLSVM: Integrating LibSVM into Weka Environment.
Tseng, Y., Lin, C., & Lin, Y. (2007). Text mining techniques for patent analysis. Information Processing & Management, 43(5), 1216-1247.