股票市場分析一直是個很有吸引力的題目。之前的研究提出了一些基於文本資料或是數據資料的分析機制。在這篇論文中，我們提出了一個結合文本資料與數據資料的方法去評估其對於股票市場中各產業的影響力。更有甚者，我們導入了空間概念將其融合在此方法中。我們的研究顯示了使用多面相的股票市場分析的準確度是相對高於單面相的。

The stock market analysis is always an attractive topic. Previous studies proposed some mechanisms to analyze by numerical data or textual data. In this paper, we provide a method to combine transaction volume and news to evaluate the influence on the industry level of the stock market. Furthermore, we introduce the spatial concept into the method. Our research shows that multiple perspectives analysis could have better precise accuracy than single perspectives analysis.

Chinese Abstract ii
Chinese Abstract iii
Acknowledgement iv
1. Introduction 1
2. Related Work 2
3. Methodology 5
3.1. Training module 6
3.1.1 Events extraction 6
3.1.2 Geographic conversion 23
3.2 Analysis model 25
3.2.1 Multiple regression analysis model 25
3.2.2 Naïve Bayesian analysis model 26
4. Experiment 28
4.1 Experimental Data 28
4.2 Experimental Setup 29
4.3 Experimental Results 30
5. Conclusion and Future work 34
Reference 36

[1] L. Blume, D. Easley, and M. O’Hara. Market statistics and technical analysis: The role of volume. Journal of Finance, 49(1):153-81, March 1994.
[2] B. Graham and D. Dodd, Security Analysis: Principles and Technique. McGraw-Hill Book Company, Inc., 1962.
[3] J. Bollen, H. Mao, and X.-J. Zeng. Twitter mood predicts the stock market, 2010.
[4] G. P. C. Fung, J. X. Yu, and W. Lam. Stock prediction: Integrating text mining approach using real-time news. Computational Intelligence For Financial Engineering, 2003. Proceedings. 2003 IEEE International Conference on, pages 395-402, 20-23 March 2003.
[5] G. P. C. Fung, J. X. Yu, and W. Lam. News sensitive stock trend prediction. Lecture Note in Computer Science, 2336:481-??, 2002.
[6] G. P. C. Fung, J. X. Yu, and H. Lu. The predicting power of textual information on financial markets. IEEE Intelligent Informatics Bulletin, 5(1):1-10, 2005.
[7] M. Gavrilov, D. Anguelov, P. Indyk, and R. Motwani. Mining the stock market (extended abstract): which measure is best? In KDD, pages 487-496, 2000.
[8] E. Gilbert and K. Karahalios. Widespread worry and the stock market. In W. W. Cohen and S. Gosling, editors, ICWSM. The AAAI Press, 2010.
[9] X. Li, X. Deng, F. Wang, and K. Dong. Empirical analysis: News impact on stock prices based one news density. In W. Fan, W. Hsu, G. I. Webb, B. Liu, C. Zhang, D. Gunopulos, and X. Wu, editors, ICDM Workshops, pages 585-592. IEEE Computer Society, 2010.
[10] G. Salton and C. Buckley. Term-weighting approaches in automatic text retrieval. In INFORMATION PROCESSING AND MANAGEMENT, pages 513-523, 1988.
[11] R. P. Schumaker and H. Chen. A discrete stock price prediction engine based on financial news. IEEE Computer, 43(1):51-56, 2010.
[12] B. Wüthrich, D. Permunetilleke, S. Leung, V. Cho, J. Zhang, and W. Lam. Daily prediction of major stock indices from textual WWW data. In KDD, pages 364-368, 1998.
[13] D.-H. Hsu and Y.-S. Chen, Auto-identify the influence of the events based on stock news, 2012.