根據先前的文獻指出新聞對於證券市場的影響多來自於公司獨有風險與投資人心理因素（如，反應—不足過度）。一般來說，這兩項效果對於市場指數的影響，相較對於個股的影響為弱。因此我們採用市場指數作為被解釋變數，試圖了解在解釋新聞和指數報酬、波動及成交量間的關係上是否有其他可能。即我們假設新聞仍具有解釋與預測市場指數的能力，並嘗試找出新聞在金融市場所扮演的角色。
我們的研究結果顯示情緒確實可能預測市場波動與成交量，特別是負面的財經新聞情緒，且以股票報酬相關性網絡的模組化程度代理的羊群效應，對於負面的財經新聞情緒有顯著負相關，當羊群效應越強財經負面情緒越強。該結果與Piškorec et al. (2014) 相符。他們提出由財經文本的內容與主體相似性，來衡量新聞集中性的概念（News Cohesiveness Index, NCI）。同時他們認為NCI揭露了部分市場風險—羊群行為。我們捕捉的負面財經新聞情緒是以Hsieh （2015）詞庫所構成，但Hsieh （2015）所建構的目標是由財經新聞預測公司月營收。整合來看，這可能意味著新聞情緒並非只是投資人對於未來表現的看法，同時也是觀察市場行為的窗口。

According to previous studies on news, news effect on stocks can be explained by idiosyncratic risk and investors psychology (e.g., under-overreaction to the market). In general, we consider these two effects to have less influence on market indexes. Therefore, we choose market indexes as dependent variables and attempt to find whether there is an alternative explanation through explaining and predicting an index’s return, volatility and volume. In brief, we assume news can still affect indexes, and attempt to figure out the role of news in financial markets.
Our results show news sentiment may predict market volatility and volume. In particular, “bad sentiment in financial news” and the modularity built by a stock return correlation network, which acts as proxy of herding, has a significant effect on negative news sentiment. This result is consistent with Piškorec et al. (2014). They propose the News Cohesiveness Index (NCI) which measures the similarity between the text and entities in financial corpus. They conclude NCI discloses part of system risk—herding. However, our negative news sentiment, which is measured by the dictionary proposed by Hsieh (2015), is built for predicting the movement of companies’ revenue. It may imply, our negative news sentiment is not just news sentiment, reflecting future expectation of investor, but also a ‘window’ of market behavior.

論文審定書 i
摘要 ii
ABSTRACT iii
I. INTRODUCTION 1
1.1 Background Information 1
1.2 Research Purpose 4
1.3 Research Structure 6
1.4 Research Contribution 8
II. LITERATURE REVIEW 9
2.1 Public Information 9
2.2 Investor Sentiment 12
2.3 Text Mining in Finance 14
2.4 Investor Attention 18
III. METHODOLOGY 20
3.1 Data Description 20
3.2 News Information Flow 21
3.3 Sentiment in News 23
3.4 Market Behavior and Investors’ Attention 25
3.5 Empirical Method 27
IV. EMPIRICAL RESULTS 28
4.1 Descriptive Statistics 28
4.2 News and Market Index 34
4.3 News and Market Behavior 42
V. Conclusion 46
REFERENCES 47
English literature 47
Chinese literature 56
Appendix 58
1. Difference Between Lexicons 58
2. Market Condition and Trend 91
3. Overview of Topic Model Results 94

English literature
1. Alanyali, M., H.S. Moat and T. Preis (2013), “Quantifying the relationship between financial news and the stock market”, Scientific Reports, 3.
2. Antweiler, W. and M.Z. Frank (2004), “Is All That Talk Just Noise? The Information Content of Internet Stock Message Boards”, Journal of Finance, 59, 1259-1294.
3. Baker, M. and J. Wurgler (2007), “Investor Sentiment in the Stock Market”, Journal of Economic Perspectives, 21, 129-151.
4. Baker, S.R., N. Bloom and S.J. Davis (2015), “What triggers stock market jumps?”, ASSA Meetings paper.
5. Bali, T.G., N. Cakici, X. Yan and Z. Zhang (2005), “Does Idiosyncratic Risk Really Matter?”, Journal of Finance, 60, 905-929.
6. Barberis, N., A. Shleifer and R. Vishny (1998), “A model of investor sentiment”, Journal of Financial Economics, 49, 307-343.
7. Blei, D.M. (2012), “Probabilistic topic models”, Communications of the ACM, 55, 77-84.
8. Brida, J.G., D. Matesanz and M.N. Seijas (2016), “Network analysis of returns and volume trading in stock markets: The Euro Stoxx case”, Physica A: Statistical Mechanics and its Applications, 444, 751-764.
9. Brown, G.W. and M.T. Cliff (2004), “Investor Sentiment and the near-term stock market”, Journal of Empirical Finance, 11, 1-27.
10. Brown, G.W. and M.T. Cliff (2005), “Investor Sentiment and Asset Valuation”, The Journal of Business, 78, 405-440.
11. Chang, A., S. Yu, A. Reinstein and N.T. Churyk (2016), “An Overview of Investor Sentiment in Stock Market”, North American Accounting Society Special Issue.
12. Chatrath, A., H. Miao, S. Ramchander and S. Villupuram (2014), “Currency jumps, cojumps and the role of macro news”, Journal of International Money and Finance, 40, 42-62.
13. Da, Z., J. Engelberg, and P. Gao (2015), “The sum of all fears investor sentiment and asset prices”, Review of Financial Studies, 28, 1-32.
14. Dang, and D. Duong (2016), “Improvement Methods for Stock Market Prediction using Financial News Articles”, 2016 3rd National Foundation for Science and Technology Development Conference on Information and Computer Science paper.
15. DeGennaro, R.P. and R.E. Shrieves (1997), “Public information releases, private information arrival and volatility in the foreign exchange market”, Journal of Empirical Finance, 4, 295-315.
16. DiBartolomeo, D. (2015), “Physics Meets Finance: Risk Systems That Read”, Northfield Asia Seminars.
17. Dimitrios, K. and O. Vasileios (2015), “A Network Analysis of the Greek Stock Market”, Procedia Economics and Finance, 33, 340-349.
18. Dimpfl, T. and S. Jank (2016), “Can internet search queries help to predict stock market volatility?”, European Financial Management, 22, 171-192.
19. Duong, D., T. Nguyen and M. Dang (2016), “Stock Market Prediction using Financial News Articles on Ho Chi Minh Stock Exchange” Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication, 71-76.
20. Feldman, R. and J. Sanger (2007), “The text mining handbook: advanced approaches in analyzing unstructured data”, Cambridge university press.
21. Fisher, K.L. and M. Statman (2000), “Investor Sentiment and Stock Returns”, Financial Analysts Journal, 56, 16-23.
22. Gerow, A., and M.T. Keane (2011), “Mining the web for the ‘voice of the herd’ to track stock market bubbles”, Twenty-Second International Joint Conference on Artificial Intelligence.
23. Go, A., R. Bhayani and L. Huang (2009), “Twitter sentiment classification using distant supervision”, CS224N Project Report, Stanford, 1.
24. Goldberg, Y. and O. Levy (2014), “word2vec explained: Deriving mikolov et al.'s negative-sampling word-embedding method”, arXiv preprint arXiv:1402.3722.
25. Hirshleifer, D., S.S. Lim and S.H. Teoh (2011), “Limited Investor Attention and Stock Market Misreactions to Accounting Information”, The Review of Asset Pricing Studies, 1, 35-73.
26. Hong, H. and J.C. Stein (1999), “A unified theory of underreaction, momentum trading, and overaction in asset markets”, Journal of Finance, 54, 2143-2184.
27. Hornik, K. and B. Grün (2011), “topicmodels: An R package for fitting topic models”, Journal of Statistical Software, 40, 1-30.
28. Hou, K., L. Peng and W. Xiong (2009), “A Tale of Two Anomalies: The Implication of Investor Attention for Price and Earnings Momentum”, Ohio State University and Princeton University Working paper.
29. Huang, W.Q., X.T. Zhuang and S. Yao (2009), “A network analysis of the Chinese stock market”, Physica A, 388, 2956-2964.
30. Hui, B. and P. Li (2014), “Does investor sentiment predict stock returns? The evidence from Chinese stock market”, Journal of Systems Science and Complexity, 27, 130-143.
31. Hwang, S., Y.I. Kim and J. Shin (2016), “An Analysis of Herding in Korean Stock Market Using Network Theory”, SSRN Electronic Journal, ssrn.2784687.
32. Kaya, M.I.Y. and M.E. Karsligil (2010), “Stock Price Prediction Using Financial News Articles”, 2010 2nd IEEE International Conference on Information and Financial Engineering paper, 478-482.
33. Ku, L.W. and H.H. Chen (2007), "Mining Opinions from the Web: Beyond Relevance Retrieval", Journal of American Society for Information Science and Technology, Special Issue on Mining Web Resources for Enhancing Information Retrieval, 58(12), 1838-1850.
34. Kyle, A.S., A.A. Obizhaeva, N.R. Sinha and T. Tuzun (2012), “News articles and the invariance hypothesis”, AFA 2012 Chicago Meetings Paper.
35. Le, Q. and T. Mikolov (2014), “Distributed Representations of Sentences and Documents”, Proceedings of Machine Learning Research, 32, 1188-1196.
36. Lee, S., J. Song and Y. Kim (2010), “An Empirical Comparison of Four Text Mining Methods”, Journal of Computer Information Systems, 51, 1-10.
37. Li, J. and J. Yu (2011), “Investor attention, psychological anchors, and stock return predictability”, Journal of Financial Economics, 104, 401-419.
38. Liu, Y., Z. Liu, T.S. Chua, and M. Sun (2015), “Topical Word Embeddings”, Twenty-Ninth AAAI Conference.
39. Loughran, T. and B. McDonald (2011), “When is a Liability not a Liability? Textual Analysis, Dictionaries, and 10-Ks”, Journal of Finance, 66, 35-65.
40. Mao, H., S. Counts and J. Bollen (2011), “Predicting financial markets: Comparing survey, news, twitter and search engine data”, arXiv preprint arXiv:1112.1051.
41. Mikolov, T., K. Chen, G. Corrado and J. Dean (2013), “Efficient Estimation of Word Representations in Vector Space”, ICLR Workshop paper.
42. Miller, K.L., H. Li, T.G. Zhou and D. Giamouridis (2015), “A Risk-Oriented Model for Factor Timing Decisions”, The Journal of Portfolio Management, 41, 46-58.
43. Mitra, L. and G. Mitra (2011), “The Handbook of News Analytics in Finance”, John Wiley & Sons Ltd.
44. Moat et al. (2013), “Quantifying Wikipedia usage patterns before stock market moves”, Scientific reports, 3.
45. Nassirtoussi, A.K., S. Aghabozorgi, T.Y. Wah, and D.C.L. Ngo (2014), “Text mining for market prediction: A systematic review”, Expert Systems with Applications, 41, 7653-7670.
46. Niu, L., X. Dai, J. Zhang, and J. Chen (2015), “Topic2Vec: learning distributed representations of topics”, In Asian Language Processing 2015 International Conference.
47. Ortigosa-Hernández et al. (2012), “Approaching Sentiment Analysis by using semi-supervised learning of multi-dimensional classifiers”, Neurocomputing, 92, 98-115.
48. Piškorec et al. (2014), “News Cohesiveness: an Indicator of Systemic Risk in Financial Markets”, arXiv preprint arXiv:1402.3483.
49. Ranco et al. (2016), “Coupling News Sentiment with Web Browsing Data Improves Prediction of Intra-Day Price Dynamics”, PLoS one, 11, e0146576.
50. Scholes, M.S. (1972), “The Market for Securities: Substitution Versus Price Pressure and the Effects of Information on Share Prices”, The Journal of Business, 45, 179-211.
51. Schumaker, R.P., and H. Chen (2009), “Textual analysis of stock market prediction using breaking financial news: The AZFin text system”, ACM Transactions on Information Systems, 27.
52. Schumaker, R.P., Y. Zhang, C.N. Huand and H. Chen (2012), “Evaluating sentiment in financial news articles”, Decision Support Systems, 53, 458-464.
53. Shen, J. (2008), “Idiosyncratic Volatility: Information or Noise?”, SSRN Electronic Journal, ssrn.1100756.
54. Shi, Y., W.M. Liu and K.Y. Ho (2016), “Public news arrival and the idiosyncratic volatility puzzle”, Journal of Empirical Finance, 37, 159-172.
55. Sung, C. W. (2016), “The Relationship between Information Network Topology and Stock market”, National Sun Yat-sen University Master Thesis.
56. Takeda, F. and T. Wakao (2014), “Google search intensity and its relationship with returns and trading volume of Japanese stocks”, Pacific-Basin Finance Journal, 24, 1-18.
57. Teoh, S.H., I. Welch and T.J. Wong (1998), “Earnings Management and the Long-Run Market Performance of Initial Public Offerings”, Journal of Finance, 53, 1935-1974.
58. Tetlock, P.C. (2007), “Giving Content to Investor Sentiment: The Role of Media in the Stock Market”, Journal of Finance, 62, 1139-1168.
59. Veronesi, P. (1999), “Stock market overreactions to bad news in good times: a rational expectations equilibrium model”, Review of Financial Studies, 12, 975-1007.
60. Vespignani, A. (2009), “Predicting the behavior of techno-social systems” Science, 325, 425-428.
61. Wang, Y. (2014), “Stock price direction prediction by directly using prices data: an empirical study on the KOSPI and HIS”, International Journal of Business Intelligence and Data Mining, 9, 145-160.
62. Wu, X., I. Ide, and S. Satoh “Large-scale news topic tracking and key-scene ranking with video near-duplicate constraints”, Proceedings of the First ACM workshop on Large-scale multimedia retrieval and mining paper, 129-136.
63. Zhang, W. and S. Skiena (2010), “Trading Strategies to Exploit Blog and News Sentiment”, In Icwsm.
64. Zhang, Y., W. Song, D. Shen and W. Zhang (2016), “Market reaction to internet news: Information diffusion and price pressure”, Economic Modelling, 56, 43-49.
Chinese literature
1. 吳忠澄 (2012)，「使用不同語意模型分析線上部落格文件」，國立東華大學資訊管理研究所碩士論文。
2. 林宜萱 (2013)，「財經領域情緒辭典之建置與其有效性之驗證 - 以財經新聞為元件」，國立臺灣大學會計學研究所碩士論文。
3. 周智勳與丁泓丞 (2013)，「基於關聯度指標之網路文件語意分析與文句摘要」，資訊科技與應用期刊，第七卷，第三期，頁89-94。
4. 陳俊達 (2007)，「以文件分類技術預測股價趨勢」，國立政治大學資訊科學研究所碩士論文。
5. 陳林志、陳大仁、葉國暉與吳忠澄 (2015)，「使用語意模型分析線上部落格文件」，中華民國資訊管理學報，第二十二卷，第三期，頁273-316。
6. 程守雄 (2010)，「股市新聞預測股價漲跌」，建國科技大學資訊管理系研討會論文。
7. 蔡彥卿 (2001)，「台灣股票市場是否充分反映已公開之財務資訊 - 月營收與季報資訊之結合」，行政院國家科學委員會專題研究計畫成果報告。
8. 謝委霖 (2015)，「從財金新聞預測公司財報之營收走勢」，國立中山大學資訊管理學系研究所碩士論文。
9. 龐磊、李壽山、張慧與周國棟 (2012)，「基於微博的股票投資者未來情感傾向識別研究」，計算機科學，第三十九卷，第6A期，頁249-252。