第五章 結論
第二節 未來研究方向
國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
49
第二節 未來研究方向
本研究整合文字探勘領域於類神經網路預測模型，透過分群分類技術使預測 模型能達到學習能力，研究成果亦顯示能顯著提高預測能力。針對未來之研究方 向，本節提出以下三點建議：
1. 本研究以詞頻及權重值高低篩選、選擇關鍵字，用以建立類別詞庫，此處提 出類別關鍵字選擇之概念。而目前網站上往往具有分類功能，類別選擇卻需 要透過人工決定，若能將此概念應用於網站上，將新的文章或網頁與類別詞 庫做相似度比對，使其能夠完成自動分類，將能帶來便利之處。然而類別詞 庫之正確程度將直接影響分類之準確度，因此若類別詞庫可隨著時間動態新 增或修正，將使其可信度大幅提高。
2. 本研究僅以時間作為切割，用縱斷面角度針對每天的新聞之分群分類結果預 測隔日收盤價，然而以橫斷面的角度來看，大型新聞事件通常會持續發展一 段時間，若能將縱斷面及橫斷面之訊息加以結合，將能提供更完整的新聞事 件資訊，相信也能得到較準確之預測能力。
3. 本研究針對半導體類股進行分析討論，若將範圍縮小至個股，則質化資料除 了新聞文件外，亦可涵蓋該公司所提供之財報資料或重大訊息等資訊，此方 式可提高非結構化資訊之完整度，而各產業所建立的類別詞庫，亦可用於討 論不同產業之依賴關係。
‧
1. K. Aas and L. Eikvil(1999), Text Categorization: a Survey, Technical Report, no.941, Norwegian Computing Center.
2. Abrahart R. J., See L. & Kneale P. E. (1998). New Tools for Neurobydrologists:
Using Network Pruning and Nodel Breeding Algorithms to Discover Optimum Inuts and Architectures. In Proceedings of the 3rd International Conference on Geocomputation. University of Bristol.
3. Ahmad, K., Oliveira, P., Manomaisupat, P., Casey, M. & Taskay, T. (2002).
Description of Events: An Analysis of Keywords and Indexical Names, Third International Conference on Language Resources and Evaluation, LREC 2002:
Workshop on Event Modelling for Multilingual Document Linking, p29-35.
4. Allan, J., Papka, R. & Lavrenko. V. (1998). On-line New Event Detection and Tracking, Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, p37-45.
5. Annexstein, F. (2002). Indexing and Representation: The Vector Space Model Retrieved, December 25, 2003, from the World Wide Web:
http://www.ececs.uc.edu/~annexste/Courses/cs690/Indexing%20and%20Represe ntation.ppt.
6. Armano G., Marchesi M., & Murru A. (2005). A hybrid
genetic-neuralarchitecture forstock indexes forecasting,” Information Sciences, Vol.170, Issue 1, p3-33.
‧
7. Chen, A. S., Leung, M. T., Daouk, H. (2003). Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index.
Computers & Operations Research. 30, 6.
8. Dawson C. W. and Wilby R. L. (2001). Hydrological Modeling Using Artificial Neural Networks. Progress in Physical Geography. 25(1), p80-108.
9. Fayyed, U., Piatetsky-Shapiro, G. & Smyth, P. (1996). The KDD Process of Extracting Useful Knowledge from Volumes of Data, Communication of the ACM, Vol.39, p27-34.
10. Ham F. M. & Kostanic I. (2001). Principles of Neurocomputing for Science &
Engineering. McGraw-Hill: New York, NY.
11. Hsu, C. W., Chang, C. C., and Lin, C. J. (2010). A Practical Guide to Support Vector Classification http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf 12. Hush, D. R. & Horne, B. G. (1993). Progress in supervised neural
networks. IEEE Signal Process. Mag. (January 1993), p8-39.
13. Jing, L. P. , Huang, H. K., Shi, H. B. (2002). Improved Feature Selection Approach TFIDF in Text Mining. 1st International Conference on Machine Learning and Cybernetics, Beijing.
14. Joachims, T. (1998). Text Categorization with Support Vector Machines:
Learning with Many Relevant Features, Proceedings of the European Conference on Machine Learning Springer.
15. Han, J. & Kamber, M. (2001). Data Mining: Concepts and Techniuqes, Morgan Kaufmann Publishers, San Francisco, CA.
16. Kim, K. J., Han, I. (2000). Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index.
‧
17. Kurt, H. (2001). On-line new event detection and tracking in a multi-resource environment, MS Thesis, The Institute of Engineering and Science of Bilkent University.
18. Kwok, T.Y. & Yeung, D. Y. (1997). Constructive Algorithms for Struture Learning in Feedforward Neural Networks for Regression Problems. IEEE Transactions on Neural Networks. 3: 630-645.
19. Kwok, T. Y. and Yeung, D. Y. (1997). Constructive Algorithms for Structure Learning in Feedforward Neural Networks for Regression Problems. IEEE Transcations on Neural Networks. 3: 630-645.
20. Lavrenko, V., Schmill, M., Lawrie, D., Ogilvie, P., Jensen, D., and Allan, J.
(2000). Language models for financial news recommendation. In Proceedings of CIKM 2000, p389-396, New York, N.Y., ACM Press.
21. Liu, H. & Motoda, H. (1998). Feature Selection for Knowledge Discovery and Data Mining. Kluwer Academic, Norwell, MA, USA.
22. MacQueen, J. (1967). Some Methods for Classification and analysis of multivariate observations. Proc. 5th Berkeley Symp. Math. Statist, Prob., 1:281-297.
23. Nguyen, D. & Widrow, B. (1990). Improving the Learning Speed of the 2-Layer Neural Networks by Choosing Initial Values of Adaptive Weights. In Proceedings of the International Joint Conference on Neural Networks. 3. San Diego, CA.
24. Nygren, K. (2004), Stock Prediction – A Neural Network Approach. Master Thesis, Royal Institute of Technology, KTH.
25. Popescu, A. (2001). Implementation of term weighting in a simple IR system, Personal course project, University of Helsinki.
26. Salton, G. (1989). Automatic Text Processing. Addison-Wesley, Reading, Mass.
‧
27. Salton, G. & Gill, M. (1983). Introduction to Modern Information Retrieval, McGraw-Hill.
28. Salton, G., Wong, A. & Yang, C. S. (1975). A Vector Space Model for Automatic Indexing.
29. Sebastiani, F. (2002). Machine learning in automated text categorization. ACM Computing Surveys, 34(1), p1-47.
30. Yang, Y., Ault, T., and Pierce, T. (2000). Improving text categorization methods for event tracking , Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.
31. Yang, Y. & Pedersen, J. O. (1997). A Comparative Study on Feature Selection in TextCategorization. Proceedings of the Fourteenth International Conference on Machine Learning, p412-420, Nashville, TN, USA.
32. Yang, Y., Pierce, T. & Carbonell, J. (1998). A Study on Retrospective And On-Line Event Detection , Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, p28-36.
33. Wu, Y. C. (2008). Predicting the Trend of Taiwan Weighted Stock Index with Text Mining Techniques, NCU IM.
34. Mittermayer, M.-A.(2004). Forecasting Intraday Stock Price Trends with Text Mining Techniques. In: Proceedings 37th Annual Hawaii Int. Conference on System Sciences (HICSS). Big Island, p64.
‧
[9]章秉純、許清琦, Combining Unsupervised Feature Selection Strategy for Automatic Text Categorization, In Proceedings of the 6th Conference on Artificial Intelligence and Applications, November 9, 2001.[10]張斐章、張麗秋，2005，類神經網路，台北市：東華書局
‧ 國
立 政 治 大 學
‧
Na tiona
l Ch engchi University
55
[14]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，10，1
[15]戴尚學，2003，運用事件偵測與追蹤技術於中文多文件摘要之研究，國立雲 林科技大學資訊管理研究所碩士論文
[16]顧皓光，1996，網路文件自動分類，國立台灣大學資訊管理研究所碩士論文 [17]羅華強，2001，類神經網路，台北市：清蔚科技
網站資料
[1]A Tutorial on Clustering Algorithms (2011), 2011 年 2 月 3 日取自 http://home.dei.polimi.it/matteucc/Clustering/tutorial_html/kmeans.html
[2]自由時報電子報。2011 年 2 月 1 日取自 http://www.libertytimes.com.tw/index.htm [3]中研院 CKIP。2011 年 1 月 17 日取自 http://ckipsvr.iis.sinica.edu.tw
[4]Yahoo API (2011)。2011 年 1 月 22 日取自 http://tw.developer.yahoo.com/cas