臺灣博碩士論文加值系統

一直以來，股票價格的趨勢預測是個令人感興趣的議題，若投資人能夠事先得知股票價格的漲跌趨勢，那麼他們較有機會從股票市場獲利。傳統的股票投資決策方式係關注與金融及資本動向相關之指數，隨著社群網路的發達，不少投資者也開始將社群網路的聲浪納入投資的參考。究竟股價波動幅度較大的期間，社群網站聲浪是否與預測準確度有顯著關係？這是本研究所關心的議題。本研究從「臺灣證券交易所」擷取2018年台積電(2330)每日三大法人買賣超資料，共計244日的參考數據，透過主成分分析(Principal Component Analysis，PCA)取得變數，再使用支援向量機(Support Vector Machine，SVM)建立預測模型來預測股價隔日漲跌準確度。至於聲浪的部分，本研究運用中研院開發之中文斷詞系統(Chinese Knowledge Information Processing Group，CKIP)處理文件進行斷詞，並建立社群網站詞組規則以萃取文章之情緒詞與程度詞，將社群網站評論文章量化為聲浪分數。據此以探討具社群網站聲浪分數修正後之模型是否比原預測模型有較佳的準確度表現。研究結果顯示，在股價波動幅度較大的期間，具聲浪分數修正之模型有較好的預測準確度。

Forecasting stock price has been always an interesting topic. If investors are able to forecast the trend of stock price, they can get the profit from stock market. However, human behavior is quite difficult to control, so it’s very difficult to predict the trend of stock price accurately. This research aim to investigate whether the score in social media has a significant relationship with the accuracy of predicted stock price during the period when the stock price of Taiwan Semiconductor Manufacturing Company (TSMC) has changed significantly. We obtain variable according to PCA(Principal Component Analysis), and builds a predictive model by SVM(Support Vector Machine) according to 244 daily records of Taiwan Semiconductor Manufacturing Company (2330) institutional investors' buy and sell data in 2018 from Taiwan Stock Exchange (TWSE) website to predict the accuracy of stock price fluctuation in next day. We do Chinese character segmentation by CKIP (Chinese Knowledge Information Processing Group) which developed by Academia Sinica. And create phrase extracting rule from social media for word related to emotion and level. Finally, whether the model which correct by the score of the investors’ online opinions is more reliable then original one. According to the research, the model has correction by the score of the investors’ online opinions is more reliable when the stock price fluctuates greatly.

摘要.................................i
Abstract............................ii
表目錄.............................iii
圖目錄..............................iv
第一章　緒論.........................1
第一節 研究動機.....................1
第二節 研究目的.....................2
第二章 文獻探討.....................3
2.1 股市預測之研究...................3
2.2 應用社群媒體預測股市的文獻回顧...4
第三章 研究方法.....................8
3.1. 研究架構.....................8
3.2. 研究方法....................10
第四章 研究結果....................18
4.1. SVM預測模型建立.............18
4.2. 社群網站聲浪修正模型........19
第五章 結論與建議..................22
5.1 研究結論........................22
5.2 研究貢獻........................23
5.3 未來研究方向....................23
參考文獻............................24

1.李宏杰 (2018)。運用文字探勘分析市場消息中關鍵詞彙與臺灣股市之關聯性-以科技股, 食品股為例。臺灣大學國際企業學研究所學位論文。
2.許溪南(2011)。台灣股票市長成分波動性之分解、趨勢與影響因素。中華管理評論國際學報第14卷第2期，頁1-頁27。
3.黃于甄(2012)。運用 TAR 模型檢測隨機漫步理論：以台灣股票市場為例。朝陽科技大學保險金融管理系學位論文。
4.黃雅鈴、洪藯珉、黃嘉敏、陳昕(2015)。文字探勘應用於選舉民意調查之研究。國立勤益科技大學。資訊管理系專題報告
5.黃筑均(2017)。使用文字探勘結合多元有順序類別支持向量機預測股價漲跌趨勢之應用。淡江大學統計學系碩士班學位論文。
6.蘇珍琦(2013)。應用情感分析技術於臺灣股票加權指數預測之研究。元智大學資訊管理學系碩士論文
7.Ballings, M., Van den Poel, D., Hespeels, N., & Gryp, R. (2015). Evaluating multiple classifiers for stock price direction prediction. Expert Systems with Applications, 42(20), 7046-7056.
8.Fung, G. P. C., Yu, J. X., & Lam, W. (2002, May). News sensitive stock trend prediction. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (pp. 481-493). Springer, Berlin, Heidelberg.
9.Huang J.Y. . Web mining for the mayoral election prediction in Taiwan, Aslib Journal of Information Management. Vol.69, No.6, pp.688-701, 2017.
10.Huang J.Y. , Liu J.H. . Using Social Media Mining Technology to Improve Stock Price Forecast Accuracy. Journal of Forecasting, accepted, 2019.
11.Katz, M. L., & Shapiro, C. (1985). Network externalities, competition, and compatibility. American economic review, 75(3), 424-440.
12.Kietzmann, J. H., Hermkens, K., McCarthy, I. P., & Silvestre, B. S. (2011). Social media? Get serious! Understanding the functional building blocks of social media. Business horizons, 54(3), 241-251.
13.Li, Z., & Tam, V. (2017, November). A comparative study of a recurrent neural network and support vector machine for predicting price movements of stocks of different volatilites.
14.Mittermayer, M. A. (2004, January). Forecasting intraday stock price trends with text mining techniques. In system sciences, 2004. Proceedings of the 37th annual Hawaii international conference on.
15.Micu, A., Mast, L., Milea, V., Frasincar, F., & Kaymak, U. (2009). Financial news analysis using a semantic web approach. In Semantic knowledge management: an ontology-based framework (pp. 311-328). IGI Global.
16.Pagolu, V. S., Reddy, K. N., Panda, G., & Majhi, B. (2016, October). Sentiment analysis of twitter data for predicting stock market movements. In 2016 international conference on signal processing, communication, power and embedded system (SCOPES) (pp. 1345-1350). IEEE.
17.Sullivan, D. (2001). Document warehousing and text mining: techniques for improving business operations, marketing, and sales. John Wiley & Sons, Inc.
18.Turney, P. D. (2002). Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. In Proceedings of the 40th annual meeting on association for computational linguistics (417-424). Association for Computational Linguistics.
19.Wuthrich, B., Cho, V., Leung, S., Permunetilleke, D., Sankaran, K., & Zhang, J. (1998, October). Daily stock market forecast from textual web data. In SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No. 98CH36218) (Vol. 3, pp. 2720-2725). IEEE.
20.Xu, W., Li, T., Jiang, B., & Cheng, C. (2012). Web Mining For Financial Market Prediction Based On Online Sentiments. In PACIS (p. 43).
21.Yu, H., Chen, R., & Zhang, G. (2014). A SVM stock selection model within PCA. Procedia computer science, 31, 406-412.
22.Zhuang, L., Jing, F., & Zhu, X. Y. (2006, November). Movie review mining and summarization. In Proceedings of the 15th ACM international conference on Information and knowledge management (pp. 43-50). ACM.
23.機器學習的世界(2017)。https://kknews.cc/zh-tw/health/68vrb6p.html (March 03, 2019)。
24.David (2015). https://www.largitdata.com/course/15/ (Jan 15, 2019)
25.IeVirve. (2018). https://github.com/leVirve/CrawlerTutorial (Jan 15, 2019)
26.jwlin. (2018). https://github.com/jwlin/ptt-web-crawler (Jan 15, 2019)
27.Mr. Opengate. (2015). https://mropengate.blogspot.com/2015/03/support-vector-machines-svm.html(March 03, 2019)
28.O’Reilly, T. . (2005). https://www.oreilly.com/pub/a/web2/archive/what-is-web-20.html(March 03, 2019)
29.skydome20 (2017). https://rpubs.com/skydome20/R-Note14-SVM-SVR