公司公開揭露的資訊有多種來源與表達揭露形式，以外部人最常使用之資訊—公司 年報就包含了由各種財務數字所組成的數值資訊與其他以文字敘述揭露的相關資訊。然 而，財務數字資訊僅能反映出公司之過去營運表現，而文字資訊則包含了許多前瞻性資 訊。年報中致股東報告書正是以公司管理階層的角度對公司營運做短期及長期分析，管 理階層對於所揭露之內容有其自由裁量權，近年來有許多文獻發現這些文字揭露是具資 訊內涵之有用資訊。因此本研究探討不同公司在致股東報告書中的文本特性，以及不同 於數值揭露，這些文字資訊是否也隱含資訊內涵，能增加對公司未來風險預測的能力， 與公司裁罰案件有關。
本研究以文字探勘技術、內容分析法與自然語言處理對台灣金融業公開發行以上之 公司 2016 年至 2017 年公司年報中致股東報告書部分進行分析。研究發現被裁罰公司易 透過增加致股東報告書文字內容的方式來增加使用者之閱讀難度、易發生致股東報告書 無負責人簽名蓋章、亦會限制其文字內容無法被分析使用;針對致股東報告書內容會傾 向陳述受到外部環境之影響段，但對於該公司今年之營運計畫較少指出具體之營運數字， 僅是以一般的文字敘述帶過。擁有上述特性之公司未來也有較高之機率發生裁罰案件。

The public information of the enterprises comes from multiple sources and comes in various types of disclosure. For instance, the annual report which most outsiders exploit discloses both numerical information of financial statement and other textual information. The textual information contains forward-looking disclosures; however, the numerical information can only reflect the past operating performances. The report to the shareholders provides investors an opportunity to understand both the short-term and long-term operations of the company through the eyes of the management and the content are largely voluntary. Prior research has discovered that the textual disclodures are informative, therefore, this study explores the attribute of the textual information from the report to the shareholders. Furthermore, in contrast with numerical information, whether the textul information is informative and is connected with administrative sanction.
This study applys text mining, content analysis and natural language processing to analyze the report to the shareholders section in the annual report of Taiwan’s public companies in financial industry. The results show that punished companies tend to lengthen the content of the report to the shareholders to increase the difficulty of reading, rather than to take the responsibilities for the content they disclosed and restrict the text content from being analyzed. Besides, they tend to emphasize the effect of external environment but are less likely to point out a specific range or number of the company's operating plan, which only appear in the general text. Similarly, companies with the characteristics mentioned above are more likely to be punished.

Abrahamson, E., & Amir, E. (1996). The information content of the president's letter to shareholders. Journal of Business Finance & Accounting, 23(8), 1157-1182.
Amel-Zadeh, A., & Faasse, J. (2016). The information content of 10-K narratives: comparing MD&A and footnotes disclosures. Available at SSRN 2807546.
Anderson, R. H., & Epstein, M. J. (1996). The usefulness of corporate annual reports to shareholders in Australia, New Zealand, and the United States: an international comparison. Jai Press.
Arnold, J., & Moizer, P. (1984). A survey of the methods used by UK investment analysts to appraise investments in ordinary shares. Accounting and Business Research, 14(55), 195-207.
Barron, O. E., Kile, C. O., & O'KEEFE, T. B. (1999). MD&A quality as measured by the SEC and analysts' earnings forecasts. Contemporary Accounting Research, 16(1), 75-109.
Bartlett, S. A., & Chandler, R. A. (1997). The corporate report and the private shareholder: Lee and Tweedie twenty years on. The British Accounting Review, 29(3), 245-261.
Beatty, A. L., Ke, B., & Petroni, K. R. (2002). Earnings management to avoid earnings declines across publicly and privately held banks. The accounting review, 77(3), 547-570.
Berelson, B. (1952). Content analysis in communication research.
Beyer, A., Cohen, D. A., Lys, T. Z., & Walther, B. R. (2010). The financial reporting environment: Review of the recent literature. Journal of accounting and economics, 50(2-3), 296-343.
Bowers, J. W. (1970). Content analysis. In Philip. Emmert & William. D. Brooks(Eds.), Methods in research in communication, 291-314. Boston, Mass:Houghton Mifflin.
Brown, S. V., & Tucker, J. W. (2011). Large‐sample evidence on firms’ year‐over‐year MD&A modifications. Journal of Accounting Research, 49(2), 309-346.
Clarkson, P. M., Kao, J. L., & Richardson, G. D. (1999). Evidence that management discussion and analysis (MD&A) is a part of a firm's overall disclosure package. Contemporary accounting research, 16(1), 111-134.
Cohen, L., Malloy, C., & Nguyen, Q. (2018). Lazy prices (No. w25084). National Bureau of Economic Research.
Cole, C. J., & Jones, C. L. (2005). Management discussion and analysis: A review and implications for future research. Journal of Accounting Literature, 24, 135.
Courtis, J. K. (1995). Readability of annual reports: Western versus Asian evidence. Accounting, Auditing & Accountability Journal, 8(2), 4-17.
Davis, A. K., Piger, J. M., & Sedor, L. M. (2006). Beyond the numbers: An analysis of optimistic and pessimistic language in earnings press releases (No. 2006-005). Federal Reserve Bank of St. Louis.
Epstein, M. J., & Pava, M. L. (1993). The shareholder's use of corporate annual reports. Jai Press.
Feldman, R., Govindaraj, S., Livnat, J., & Segal, B. (2010). Management’s tone change, post earnings announcement drift and accruals. Review of Accounting Studies, 15(4), 915-953.
Graesser, A. C., McNamara, D. S., Louwerse, M. M., & Cai, Z. (2004). Coh-Metrix: Analysis of text on cohesion and language. Behavior research methods, instruments, & computers, 36(2), 193-202.
Jones, M. J., & Shoemaker, P. A. (1994). Accounting narratives: A review of empirical studies of content and readability. Journal of accounting literature, 13, 142.
Li, F. (2006). Do stock market investors understand the risk sentiment of corporate annual reports?. Available at SSRN 898181.
Li, F. (2008). Annual report readability, current earnings, and earnings persistence. Journal of Accounting and economics, 45(2-3), 221-247.
Li, F. (2010). The information content of forward‐looking statements in corporate filings—A naïve Bayesian machine learning approach. Journal of Accounting Research, 48(5), 1049-1102.
Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of Finance, 66(1), 35-65.
Loughran, T., & McDonald, B. (2014). Measuring readability in financial disclosures. The Journal of Finance, 69(4), 1643-1671.
McNamara, D. S., Louwerse, M. M., McCarthy, P. M., & Graesser, A. C. (2010). Coh-Metrix: Capturing linguistic features of cohesion. Discourse Processes, 47(4), 292-330.
Muslu, V., Radhakrishnan, S., Subramanyam, K. R., & Lim, D. (2014). Forward-looking MD&A disclosures and the information environment. Management Science, 61(5), 931-948.
Pang, B., & Lee, L. (2008). Opinion mining and sentiment analysis. Foundations and Trends® in Information Retrieval, 2(1–2), 1-135.
Peterson, K. (2012). Accounting complexity, misreporting, and the consequences of misreporting. Review of accounting studies, 17(1), 72-95.
Peterson, K., Schmardebeck, R., & Wilks, T. J. (2015). The earnings quality and information processing effects of accounting consistency. The accounting review, 90(6), 2483-2514.
Schipper, K. (2007). Required disclosures in financial reports. The Accounting Review, 82(2), 301-326.
Securities and Exchange Commission (SEC). 1987. Concept Release on Management's Discussion and Analysis of Financial Condition and Results of Operations. Securities Act Release No. 33-6711. Washington, D.C.: SEC.
Skinner, D. J. (1994). Why firms voluntarily disclose bad news. Journal of accounting research, 32(1), 38-60.
Smith, M., & Taffler, R. (1992). Readability and understandability: Different measures of the textual complexity of accounting narrative. Accounting, Auditing & Accountability Journal, 5(4).
Subramanian, R., Insley, R. G., & Blackwell, R. D. (1993). Performance and readability: A comparison of annual reports of profitable and unprofitable corporations. The Journal of Business Communication (1973), 30(1), 49-61.
Tetlock, P. C., Saar‐Tsechansky, M., & Macskassy, S. (2008). More than words: Quantifying language to measure firms' fundamentals. The Journal of Finance, 63(3), 1437-1467.
Tsai, M. F., & Wang, C. J. (2017). On the risk prediction and analysis of soft information in finance reports. European Journal of Operational Research, 257(1), 243-250.