進階搜尋


下載電子全文  
系統識別號 U0026-1306201916245300
論文名稱(中文) 應用深度學習分析經理人情緒並預測公司過度投資
論文名稱(英文) Apply Deep Learning to Analyze CEO’s Sentiment and Predict Firms’ Overinvestment
校院名稱 成功大學
系所名稱(中) 會計學系
系所名稱(英) Department of Accountancy
學年度 107
學期 2
出版年 108
研究生(中文) 許哲維
研究生(英文) Zhe-Wei Xu
學號 R16061205
學位類別 碩士
語文別 中文
論文頁數 38頁
口試委員 指導教授-顏盟峯
口試委員-許永明
口試委員-周庭楷
口試委員-鄭順林
中文關鍵字 深度學習  自然語言處理  情緒分析  過度投資 
英文關鍵字 Deep Learning  Natural Language Processing  Sentiment Analysis  Over-investment 
學科別分類
中文摘要 近年來因電腦硬體設備蓬勃發展讓機器學習及深度學習應用迅速崛起,除此之外亦有多項研究都表明,深度學習在自然語言處理(Natural Language Processing)的主題上有良好的成效。透過深度學習應用於文本分析將新聞媒體上的文字轉換成具體的情緒分數,並且將情緒分數運用於衡量公司經理人情緒,進而預測過度投資,此方法不只可以將文字量化成有意義的數字進行更多分析,更能夠利用分析結果進行企業分析和投資決策的依據。
因此本研究將深度學習技術應用於文本分析進而給予文字情緒分數,利用情緒分數指標代替經理人的情緒並預測過度投資。本研究發現經理人的情緒越正面時,也就是情緒分數越高會造成過度投資的增加,當經理人的情緒越負面時,也就是情緒分數越低也會造成過度投資的減少甚至投資不足,同時負向情緒對於過度投資的影響更勝於正向情緒,而研究也發現激發水準對於情緒向性存在著放大效果。
英文摘要 In recent years, the development of machine learning and deep learning have been remarkably advanced due to the rapid growth of computer hardware. In addition, many studies have shown that deep learning techniques have achieved good results in the theme of Natural Language Processing. In this study, we apply the deep learning-based textual analysis to convert texts into sentiment scores, which are then used measure CEO's sentiment to predict over-investment. By doing so, we can not only quantify texts into meaningful numbers but also make decision based on the analyzed results. We found that the sentiment scores are positively related to over-investment. Negative sentiment tends to have a greater impact on over-investment than positive sentiment. Finally, when multiplied by arousal, valence would show more explanatory power.
論文目次 第一章、緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的及貢獻 3
1.4 章節架構 5
第二章、文獻探討 6
2.1 過度投資 6
2.2 深度學習 6
2.2.1 LSTM 7
2.2.2 Bi-LSTM 8
2.2.3 CNN 9
2.3 Word2Vec詞向量模型 10
2.4 情緒分析 11
第三章、研究方法 14
3.1 資料來源與樣本選取 14
3.2 研究技術 15
3.2.1 斷詞處理 16
3.2.2 Word2Vec(詞向量產生) 17
3.2.3 Bi-LSTM、CNN類神經網路 17
3.3 變數定義與衡量 20
3.3.1 過度投資 20
3.3.2 情緒分數之衡量 21
3.4 迴歸模型設計 23
3.4.1 假說一 24
3.4.2 假說二 24
3.4.3 假說三 24
3.4.4 假說四 24
第四章、實證結果 26
4.1 敘述性統計 26
4.2 實證結果 26
4.2.1 假說一實證結果 27
4.2.2 假說二實證結果 27
4.2.3 假說三實證結果 28
4.2.4 假說四實證結果 29
第五章、結論與建議 31
5.1 研究結果 31
5.2 研究限制與建議 32
參考文獻 34

參考文獻 江易麇. (2018). 應用雙向長短期記憶神經網路於新聞分類. (碩士), 國立雲林科技大學, Retrieved from https://hdl.handle.net/11296/sexr7f

呂青樺, & 沈中華. (2017). 官員升遷, 經濟成長與地方過度投資—以中國各省為例. 兩岸金融季刊, 5(4), 1-30.

李啟華, 陳政芳, & 林丕淇. (2017). 國際會計準則對管理者過度投資行為之影響-來自新十號存貨公報之證據. 東吳經濟商學學報(94), 39-64.

蔡永順, & 劉文智. (2011). 台灣機構投資人過度自信行為實證研究. 台灣管理學刊, 11(2), 91-126.

Ahmed, A. S., & Duellman, S. (2013). Managerial overconfidence and accounting conservatism. Journal of Accounting Research, 51(1), 1-30.

Bradley, M. M., & Lang, P. J. (1994). Measuring emotion: the self-assessment manikin and the semantic differential. Journal of behavior therapy and experimental psychiatry, 25(1), 49-59.

Bradley, M. M., & Lang, P. J. (1999). Affective norms for English words (ANEW): Instruction manual and affective ratings (Vol. 30, No. 1, pp. 25-36). Technical report C-1, the center for research in psychophysiology, University of Florida.

Core, J. E., Holthausen, R. W., & Larcker, D. F. (1999). Corporate governance, chief executive officer compensation, and firm performance. Journal of Financial Economics, 51(3), 371-406.

Daniel, K., Hirshleifer, D., & Subrahmanyam, A. (1998). Investor psychology and security market under‐and overreactions. the Journal of Finance, 53(6), 1839-1885.

Das, S. R., & Chen, M. Y. (2007). Yahoo! for Amazon: Sentiment extraction from small talk on the web. Management science, 53(9), 1375-1388.

Guan, Z., Chen, L., Zhao, W., Zheng, Y., Tan, S., & Cai, D. (2016). Weakly-Supervised Deep Learning for Customer Review Sentiment Classification. Paper presented at the IJCAI.

Harford, J. (1999). Corporate cash reserves and acquisitions. the Journal of Finance, 54(6), 1969-1997.

Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.

Jensen, M. C. (1986). Agency costs of free cash flow, corporate finance, and takeovers. The American economic review, 76(2), 323-329.

Ji, S., Xu, W., Yang, M., & Yu, K. (2013). 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221-231.

Kamaruddin, N., & Rahman, A. W. A. (2013). Valence-arousal approach for speech emotion recognition system. Paper presented at the 2013 International Conference on Electronics, Computer and Computation (ICECCO).

Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882.

Lang, L. H., & Litzenberger, R. H. (1989). Dividend announcements: Cash flow signalling vs. free cash flow hypothesis? Journal of Financial Economics, 24(1), 181-191.

Lang, P. J. (1980). “Behavioral treatment and bio-behavioral assessment: Computer applications.” In J. B. Sidowski, J. H. Johnson, and T. A. Williams (Eds.), Technology in mental health care delivery systems (pp. 119–137). Norwood, NJ: Ablex.

Lenard, M. J., & Yu, B. (2012). Do earnings management and audit quality influence over-investment by Chinese companies. International Journal of Economics and Finance, 4(2), 21-30.

Lie, E. (2000). Excess funds and agency problems: an empirical study of incremental cash disbursements. The Review of Financial Studies, 13(1), 219-248.

Mazboudi, M. (2012). Accounting choices under IFRS and their effect on over-investment in capital expenditures.

Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Paper presented at the Advances in neural information processing systems.

Mäntylä, M., Adams, B., Destefanis, G., Graziotin, D., & Ortu, M. (2016). Mining valence, arousal, and dominance: possibilities for detecting burnout and productivity? Paper presented at the Proceedings of the 13th International Conference on Mining Software Repositories.

Preoţiuc-Pietro, D., Schwartz, H. A., Park, G., Eichstaedt, J., Kern, M., Ungar, L., & Shulman, E. (2016). Modelling valence and arousal in facebook posts. Paper presented at the Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis.

Richardson, S. (2006). Over-investment of free cash flow. Review of accounting studies, 11(2-3), 159-189.

Russell, J. A. (1980). A circumplex model of affect. Journal of personality and social psychology, 39(6), 1161-1178.

Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673-2681.

Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., . . . Lanctot, M. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484-489.

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. (2013). Risk ranking from financial reports. Paper presented at the European Conference on Information Retrieval.

Wang, C.-J., Tsai, M.-F., Liu, T., & Chang, C.-T. (2013). Financial sentiment analysis for risk prediction. Paper presented at the Proceedings of the Sixth International Joint Conference on Natural Language Processing.

Wang, J., Yu, L.-C., Lai, K. R., & Zhang, X. (2016). Dimensional sentiment analysis using a regional CNN-LSTM model. Paper presented at the Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).

Wang, J., Yu, L.-C., Lai, K. R., Zhang, X.(2016). Community-based weighted graph model for valence-arousal prediction of affective words. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 24(11), 1957-1968.

Weinstein, N. D. (1980). Unrealistic optimism about future life events. Journal of personality and social psychology, 39(5), 806.

Yu, L.-C., Lee, L.-H., Hao, S., Wang, J., He, Y., Hu, J., Lai, R., and Zhang, X. (2016). Building Chinese affective resources in valence-arousal dimensions. Paper presented at the Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.

Zhang, X., Zhao, J., & LeCun, Y. (2015). Character-level convolutional networks for text classification. In Advances in neural information processing systems (pp. 649-657).
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2019-07-05起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2019-07-05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