進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1907202019440700
論文名稱(中文) 以文字探勘技術探討臺灣上市公司之關鍵查核事項資訊內涵與財務績效之關聯性
論文名稱(英文) Applying the Textual Mining Technique to Study the Association between the Information Content of Key Audit Matters of Taiwan Listed Companies and Financial Performance
校院名稱 成功大學
系所名稱(中) 經營管理碩士學位學程(AMBA)
系所名稱(英) Advanced Master of Business Administration (AMBA)
學年度 108
學期 2
出版年 109
研究生(中文) 吳岱螢
研究生(英文) Tai-Ying Wu
學號 RD6074157
學位類別 碩士
語文別 中文
論文頁數 46頁
口試委員 指導教授-顏盟峯
口試委員-許永明
口試委員-許英麟
中文關鍵字 關鍵查核事項  文字探勘  情感分析  財務績效 
英文關鍵字 Key Audit Matters  Text Mining  Sentiment Analysis  Financial Performance 
學科別分類
中文摘要 我國於西元2016年參酌國際審計準則第701號(ISA 701「Communicating Key Audit Matters in the Independent Auditor's Report)」)後,於同年4月12日發布了審計準則公報第58號「查核報告中關鍵查核事項之溝通」,會計師依該公報之規定應依其專業之判斷揭露查核公司之關鍵查核事項(Key Audit Matters),以降低審計預期落差並提高資訊透明度,惟部分無專業背景之投資人於閱讀查核報告時,對該內容仍有理解上之困難。在人工智慧與機器學習蓬勃發展之時代,相關技術之運用已成為各產業之趨勢,而文字探勘技術中的情感分析運用在波動性大且資訊較不透明的虛擬貨幣、房地產之未來價格預測上都有著亮眼的成績,故本研究欲以文字探勘技術來探討關鍵查核事項所隱含之情緒向性與企業之財務績效間之關聯性,以提供投資人另一更直觀的參考指標。
本研究採用Google所開發之自然語言處理預訓練的模型(Bidirectional Encoder Representation from Transformer;BERT),對我國上市公司於西元2016年至2018年間發布之會計師查核報告中的關鍵查核事項,以文字探勘之方式萃取其情緒向性,以前兩年之關鍵查核事項共3,366筆中的80%作為訓練樣本,20%作為驗證樣本訓練BERT模型,再以2018年度807家上市公司之1,527筆關鍵查核事項作為預測樣本後進行分析,探討該情緒向性與公司財務績效間之關聯性,本研究之實證結果如下:
一、關鍵查核事項之情緒向性與當年度之市場績效成正相關。
二、關鍵查核事項之情緒向性與下一年度之市場績效成正相關。
三、關鍵查核事項之情緒向性與當年度之會計績效並無顯著相關。
四、關鍵查核事項之情緒向性與下一年度之會計績效成正相關。
英文摘要 According to Statement on Auditing Standard(SAS) No. 58, auditors shall disclose the Key Audit Matters(KAMs) in the audit reports to reduce the audit expectation gap and improve the information disclosure transparency. However, the content of audit reports is difficult to understand for some investors. Today, artificial intelligence (AI) is a booming field with numerous practical applications and on-going research topics. The sentiment analysis achieved the great performance in predicting for digital currency and real estate market, therefore, this study applies the textual mining technique to examine the association between the emotional valence of KAMs and the financial performance of companies, which provides another intuition index for investors.
This study analyzes the information content of KAMs of Taiwan listed companies for sentiment analysis with deep learning by using BERT, which is a technique for NLP (Natural Language Processing) pre-training developed by Google. There are 3,366 KAMs from 2016 to 2017, we use 80% of dataset and 5-fold cross-validation to train the model, and use 20% of the dataset as the test dataset. And the remaining 1,527 KAMs in 2018 are predicted based on the trained model. Overall, this study shows that the emotional valence of KAMs has a positive correlation with the marketing performance of the current year and the coming year. And the emotional valence of KAMs has a positive correlation with the financial accounting performance of the coming year, while no correlative outcome for the current year.
論文目次 第一章 緒論 1
第一節 研究背景、動機與目的 1
第二節 研究問題 4
第三節 研究流程 5
第二章 文獻探討 6
第一節 關鍵查核事項 6
第二節 深度學習(Deep learning)與文字探勘(Text Mining) 13
第三節 情感分析相關文獻 15
第三章 資料來源與研究方法 16
第一節 資料來源與樣本前處理 16
第二節 深度學習模型 18
第三節 研究假說與迴歸模型設計 22
第四章 實證結果 28
第一節 敘述性統計與相關係數矩陣 28
第二節 迴歸分析 33
第五章 結論與建議 39
第一節 研究結果 39
第二節 研究限制 40
第三節 未來研究建議 41
參考文獻 42
中文文獻 42
英文文獻 42
網路資料 46
參考文獻 中文文獻
李建然. (2016). 財務報表使用者如何解讀上市 (櫃) 公司新式無保留意見查核報告. 證券暨期貨月刊, 34(9), 頁16-29.
李建然. (2017). 新式會計師查核報告實施後會計師應注意事項及其可能之衝擊. 會計師季刊, 270期, 頁8-13.
吳映儀. (2018). 關鍵查核事項與分析師預測行為之關聯性—基於台灣的實證研究.
許詠婷. (2017). 會計師新式查核報告是否提供增額資訊給投資人? 來自英國的證據.
黃旭輝, 林佳慧, 黃一祥, & 張志向. (2011). 修正式無保留意見是否預告了公司不佳的經營績效? 管理與系統, 18(2), 頁239-266.

英文文獻
Asare, S. K., & Wright, A. M. (2012). Investors', auditors', and lenders' understanding of the message conveyed by the standard audit report on the financial statements. Accounting Horizons, 26(2), p193-217.
Bédard, J., Gonthier-Besacier, N., & Schatt, A. (2014). Costs and benefits of reporting Key Audit Matters in the audit report: The French experience. Paper presented at the International Symposium on Audit Research.
Barontini, R., & Caprio, L. (2006). The effect of family control on firm value and performance: Evidence from continental Europe. European Financial Management, 12(5), p689-723.
Brasel, K., Doxey, M. M., Grenier, J. H., & Reffett, A. (2016). Risk disclosure preceding negative outcomes: The effects of reporting critical audit matters on judgments of auditor liability. The Accounting Review, 91(5), p1345-1362.
Chen, L., Jones, K. L., Lisic, L. L., Michas, P., Pawlewicz, R., & Pevzner, M. B. (2013). Comments by the auditing standards committee of the auditing section of the American Accounting Association on the IAASB proposal: Improving the auditor's report: participating committee members and other contributors. Current Issues in Auditing, 7(1), C11-C20.
Chong, K. M., & Pflugrath, G. (2008). Do different audit report formats affect shareholders' and auditors' perceptions? International Journal of Auditing, 12(3), p221-241.
Christensen, B. E., Glover, S. M., & Wolfe, C. J. (2014). Do critical audit matter paragraphs in the audit report change nonprofessional investors' decision to invest? Auditing: A Journal of Practice & Theory, 33(4), p71-93.
Church, B. K., Davis, S. M., & McCracken, S. A. (2008). The auditor's reporting model: A literature overview and research synthesis. Accounting Horizons, 22(1), p69-90.
Connolly, R. A., & Hirschey, M. (2005). Firm size and the effect of R&D on Tobin's q. R&D Management, 35(2), p217-223.
Czerney, K., Schmidt, J. J., & Thompson, A. M. (2019). Do investors respond to explanatory language included in unqualified audit reports? Contemporary Accounting Research, 36(1), p198-229.
Davis, R. R. (1982). “An Empirical Evaluation of Auditor's Subject-to Opinions,” Auditing: A Journal of Practice and Theory, 2(1), pp. 13-32.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Dodd, P., Dopuch, N., Holthausen, R., & Leftwich, R. (1984). Qualified audit opinions and stock prices: Information content, announcement dates, and concurrent disclosures. Journal of Accounting and Economics, 6(1), p3-38.
Dopuch, N., Holthausen, R. W., & Leftwich, R. W. (1986). Abnormal stock returns associated with media disclosures of ‘subject to’ qualified audit opinions. Journal of Accounting and Economics, 8(2), p93-117.
Fields, L. P., & Wilkins, M. S. (1991). The information content of withdrawn audit qualifications: new evidence on the value of “subject-to” opinions. A Journal of Practice & Theory, 10(2), p62-69.
Gimbar, C., Hansen, B., & Ozlanski, M. E. (2016). The effects of critical audit matter paragraphs and accounting standard precision on auditor liability. The Accounting Review, 91(6), p1629-1646.
Gutierrez, E., Minutti-Meza, M., Tatum, K. W., & Vulcheva, M. (2018). Consequences of adopting an expanded auditor’s report in the United Kingdom. Review of Accounting Studies, 23(4), p1543-1587.
Kachelmeier, S., Schmidt, J., & Valentine, K. (2018). Do critical audit matter disclosures protect auditors by forewarning users of misstatement risk. Working paper, University of Texas at Austin.
Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.
Köhler, A., Ratzinger-Sakel, N., & Theis, J. (2020). The effects of key audit matters on the auditor’s report’s communicative value: Experimental evidence from investment professionals and non-professional investors. Accounting in Europe, DOI: 10.1080/17449480.2020.1726420
Lee, T. H., Ali, A. M., & Bien, D. (2009). Towards an understanding of the audit expectation gap. ICFAI Journal of Audit Practice, 6(1), p7-35.
Mock, T. J., Bédard, J., Coram, P. J., Davis, S. M., Espahbodi, R., & Warne, R. C. (2012). The audit reporting model: Current research synthesis and implications. Auditing: A Journal of Practice & Theory, 32(sp1), p323-351.
Reid, L. C., Carcello, J. V., Li, C., Neal, T. L., & Francis, J. R. (2019). Impact of auditor report changes on financial reporting quality and audit costs: Evidence from the United Kingdom. Contemporary Accounting Research, 36(3), p1501-1539.
Sirois, L.-P., Bédard, J., & Bera, P. (2018). The informational value of key audit matters in the auditor's report: Evidence from an eye-tracking study. Accounting Horizons, 32(2), p141-162.
Smith, K. (2019). Tell me more: A content analysis of expanded auditor reporting in the United Kingdom. Available at SSRN 2821399.
Soo, C. K. (2018). Quantifying sentiment with news media across local housing markets. The Review of Financial Studies, 31(10), p3689-3719.
Steinert, L., & Herff, C. (2018). Predicting altcoin returns using social media. PloS one, 13(12), e0208119.
Tang, D., Qin, B., & Liu, T. (2015). Document modeling with gated recurrent neural network for sentiment classification. Paper presented at the Proceedings of the 2015 conference on empirical methods in natural language processing, pp.1422-1432.
Tetlock, P. C., Saar‐Tsechansky, M., & Macskassy, S. (2008). More than words: Quantifying language to measure firms' fundamentals. The Journal of Finance, 63(3), p1437-1467.
Villalonga, B., & Amit, R. (2006). How do family ownership, control and management affect firm value? Journal of financial Economics, 80(2), p385-417.
Wang, Y., Huang, M., & Zhao, L. (2016). Attention-based LSTM for aspect-level sentiment classification. Paper presented at the Proceedings of the 2016 conference on empirical methods in natural language processing, pp. 606-615.

網路資料
LeeMeng (2019),進擊的 BERT:NLP 界的巨人之力與遷移學習。
https://leemeng.tw/index.html
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-06-29起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2023-06-29起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw