找尋股價跳躍之成因，並且量化該成因的資訊衝擊，一直是學界
常見研究課題之。近年來隨著文字分析導入財金領域，逐漸有學者以
情緒分析法將個體新聞的情緒量化為帶來資訊衝擊的指標，並且檢驗
是否可作為解釋股價跳躍之因子。然而新聞報導的焦點轉換應該也會
是影響股價跳躍的原因之一，為研究此觀點，我們採用美國 S&P500
成分股中前 75 家企業作為樣本，並從華爾街日報收集與這 75 家
公司相關的個股新聞。接著，我們以新聞主題作為新聞所報導之焦點
的代表，建立了一個量化指標，該指標包括主題和情緒隨時間變化的
資訊，用於衡量個股新聞對股價所帶來的資訊衝擊。該指標的建立概
念是，如果新事件發生且帶來資訊量足夠巨大時，將會吸引了新聞媒
體的關注焦點，導致報導的主題發生改變。我們使用機器學習方法將
新聞的主題資訊進行量化，並且使用 Loughran and McDonald (2011)
財金字典作為參考，將新聞情緒量化為數值形式。量化完主題與情緒
資訊後，我們使用向量運算方法將主題和情緒融合成上述的指標並且
檢驗其與股價跳躍之相關性。最終檢驗結果證明該指標對於股價跳躍
具有解釋力，證實新聞焦點的變化的確會造成股價跳躍的產生。

The search for the causes of stock price jumps and quantifying the
informational shock has been a common research topic in academia. In
recent years, with the introduction of text analysis in the field of finance,
scholars have used sentiment analysis to quantify the individual news
sentiment as an indicator of informational shock and examined whether it
can predict stock price jumps. However, the shifting focus of news is also
likely to be one of the factors influencing stock price jumps. To study this
perspective, we selected the top 75 companies in the US S&P 500 index as
our sample and collected stock-specific news related to these 75 companies
from The Wall Street Journal. Subsequently, we used news topics as proxy
of the news focus and create a quantification index that includes
information of change in topics and sentiment. This index is used to
measure the informational shock of news on stock prices. The underlying
concept of this index is that if a significant event occurs and generates a
substantial amount of information, it will attract the attention of the news
media, leading to a change in the reported topics. We used machine
learning methods to quantify the topic information of the news and
employed the Loughran and McDonald financial dictionary as a reference
to quantify the news sentiment in numerical form. After quantifying the
topic and sentiment information, we combined them using vector
operations to create the aforementioned index and examined its correlation
with stock price jumps. The final test results demonstrated that this index
has explanatory power for stock price jumps, confirming that changes in
news focus indeed lead to stock price jumps.

1. Andersen, T. G., Bollerslev, T., Diebold, F. X. and C. Vega (2007), “Real-time Price Discovery in Global stock, Bond and Foreign Exchange Markets,” Journal of International Economics, 73, 251-277.
2. Balduzzi, P., Elton, E. J. and T. C. Green (2001), “Economic News and Bond Prices: Evidence from the U.S. Treasury Market,” The Journal of Financial and Quantitative Analysis, 36, 523-543.
3. Barndorff-Nielsen, O. E. and N. Shephard (2006), “Econometrics of Testing for Jumps in Financial Economics Using Bipower Variation,” Journal of Financial Econometrics, 4, 1-30.
4. Bernard, V. L. and J. K. Thomas (1989), “Evidence that Stock Prices Do Not Fully Reflect the Implications of Current Earnings for Future Earnings,” Journal of Accounting and Economics, 13, 305-340.
5. Devlin, J., Chang, M.W., Lee, K. and K. Toutanova (2018), “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” arXiv:1810.04805.
6. Doyle, J. T., Lundholm, R. J. and M. T. Soliman (2006), “The Extreme Future Stock Returns Following I/B/E/S Earnings Surprises,” Journal of Accounting Research, 44, 849-887.
7. Dumitru, A. and G. Urga (2012), “Identifying Jumps in Financial Assets: A Comparison Between Nonparametric Jump Tests,” Journal of Business & Economic Statistics, 30, 245-255.
8. Ellen, S., Larsen, V. and L. Thorsrud (2022), “Narrative Monetary Policy Surprises and the Media,” Journal of Money, Credit and Banking, 54, 1525-1549.
9. Jeon, Y., McCurdy, T. H. and X. Zhao (2022), “News as Sources of Jumps in Stock Returns: Evidence from 21 million News Articles for 9000 Companies,” Journal of Financial Economics, 145, 1-17.
10. Jiang, G. J., and Oomen, R. (2008), “Testing for Jumps when Asset Prices are Observed with Noise: A ‘Swap Variance’ Approach,” Journal of Econometrics, 144, 352–370.
11. Loughran, T. and B. McDonald (2011), “When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks,” The Journal of finance, 66, 35-65.
12. Kim, H. Y. and J.P. Mei (2001), “What Makes the Stock Market Jump? An Analysis of Political Risk on Hong Kong Stock Returns,” Journal of International Money and Finance, 20, 1003-1016.
13. Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P. and R. Soricut (2019), “ALBERT: A Lite BERT for Self-supervised Learning of Language Representations,” arXiv:1909.11942.
14. Lee, S.S. and P. A., Mykland (2008), “Jumps in Financial Markets: A New Nonparametric Test and Jump Dynamics,” The Review of Financial Studies, 21, 2535-2563.
15. Lee, S. S. (2012), “Jumps and Information Flow in Financial Markets,” The Review of Financial Studies, 25, 439-479.
16. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L. and V. Stoyanov (2019), “RoBERTa: A Robustly Optimized BERT Pretraining Approach”, arXiv:1907.11692.
17. Manela, A. and A. Moreira (2017), “News Implied Volatility and Disaster Concerns,” Journal of Financial Economics, 123, 137-162.
18. Martineau, C. (2018), “Rest in Peace Post-Earnings Announcement Drift, ” Critical Finance Review, Forthcoming.
19. Merton, R. C. (1976), “Option Pricing When Underlying Stock Returns are Discontinuous,” Journal of Financial Economics, 3, 125-144.
20. Rangel, J. G. (2011), “Macroeconomic News, Announcements, and Stock Market Jump Intensity Dynamics,” Journal of Banking & Finance, 35, 1263-1276.
21. Sharpe, W. F. (1964), “Capital Asset Prices: A Theory of Market Equilibrium under Conditions of Risk,” Journal of Finance, 19, 425-442.
22. Tetlock, P. C. (2010), “Does Public Financial News Resolve Asymmetric Information?, ” Review of Financial Studies, 23, 3520-3557.
23. Yang, Y., Li, Jing., Hseu, J., Song, X., Demmel, J. and C. J. Hsieh (2019), “Reducing BERT Pre-training Time from 3 Days to 76 Minutes,” arXiv:1904.00962.
24. Zhang, X. F. (2006), “Information Uncertainty and Stock Returns,” The Journal of Finance, 61, 105-137.