隨著網路世代的崛起，網路資訊的取得更加即時，且更具效率。外部投資人除了透過傳統的方式，於財務季度報告的揭露日期查看企業公佈的財務報表，來了解企業的財務、經營績效，亦能透過新聞媒體、財經社群網路論壇來搜尋到更多企業相關的財務績效評論，了解市場對於該企業的印象、評價如何，進而精準地做出投資決策。
隨著時代及科技的進步，運用人工智慧(Artificial Intelligence，AI)技術於文本分析(Textual Analysis)之相關研究，成了會計和金融相關領域的新興議題。如何將新聞媒體、財經社群網路論壇上的文字，透過文本分析技術的協助，進行文字情緒定義，並且將這些文字情緒分數，運用在預估一家企業未來的財務績效，不只可以最大化文本分析技術應用於會計、財經領域的貢獻，更能夠協助人類利用這些分析結果，進行日後企業走向預測參考和投資決策的進行。
本研究利用中文維度型情感詞典(Chinese Valence-Arousal Words，CVAW)取得台灣183家上市櫃公司每季的輿情分數累加數值，用於預估資產報酬率、股東權益報酬率及Tobin’s Q三項財務績效指標。本研究發現，當情緒向性整體而言為正向的輿情分數時，對公司財務績效無論是資產報酬率、股東權益報酬率及Tobin’s Q，皆具有較明顯的正向顯著預測效果；整體而言，激發水準對於情緒向性用於預測公司財務績效時，資產報酬率、股東權益報酬率及Tobin’s Q亦具有正向的調節效果。其中，激發水準對於情緒向性用於預測公司長期財務績效Tobin’s Q時，正向顯著的結果更加明顯。

With the rise of the Internet generation, getting online information is more instantaneous and more efficient. In addition to the traditional method, the external investors can not only view the financial statements published by the company on the disclosure date of the financial quarterly report to view the financial performance of the company. But also find more information through the news media and the financial community online forum.
Artificial Intelligence (AI) technology in textual analysis has become an emerging topic in accounting and finance. Using the texts of the news media and financial community online forums to help define the mood of words, and apply these emotional scores to predict the firms’ financial performance, can not only maximize the contribution of text analysis technology to accounting and financial fields, but also help humans to use these analysis results to conduct future forecasting and investment decisions.
The research used the Chinese Valence-Arousal Words (CVAW) to obtain the accumulated scores of the sentiment words of 183 listed companies in Taiwan for the estimation of return on assets, return on equity and Tobin's Q. The results show that when the sentiment is positive as a positive sentiment score, the company's financial performance has a significant positive predictive effect on both the return on assets, the return on equity, and Tobin's Q; In other words, when the emotional temperament is used to predict the company's financial performance, the return on assets, the return on equity, and Tobin's Q also have a positive adjustment effect. Among them, the positive level is more obvious when the emotional tropism is used to predict the company's long-term financial performance Tobin’s Q.

一、 中文文獻
1. 李馨蘋, & 莊宗憲. (2007). 公司治理機制與公司績效之實證研究. 東吳經濟商學學報 (57), pp. 1-27.
2. 李秀英, 劉俊儒, & 楊筱翎. (2011). 企業社會責任與公司績效之關聯性. 東海管理評論第 13 卷第一期, pp. 77-112.
3. 吳米琪. (2013). 公司治理對營運資金管理與企業價值關係之調節作用. 淡江大學會計學系碩士班學位論文, pp. 1-59.
4. 劉正田, 林修葳, & 金成隆. (2005). 創新價值鏈之路徑分析: 金業研發投資成效之實證研究. 管理評論, 24(4), pp. 29-56.
二、 英文文獻
1. Adithipyangkul, P., Alon, I., & Zhang, T. (2011). “Executive perks: Compensation and corporate performance in China.” Asia Pacific Journal of Management, 28(2), pp. 401-425.
2. Almas, Y., & Ahmad, K. (2007, July). “ A note on extracting ‘sentiments’ in financial news in English, Arabic & Urdu.”In The Second Workshop on Computational Approaches to Arabic Script-based Languages (pp. 1-12).
3. Calvo, R. A., & D'Mello, S. (2010). “Affect detection: An interdisciplinary review of models, methods, and their applications. ”IEEE Transactions on affective computing, 1(1), pp. 18-37.
4. Devitt, A., & Ahmad, K. (2008, May). “Sentiment Analysis and the Use of Extrinsic Datasets in Evaluation.” In LREC.
5. Erdogan, B. E. (2013). “Prediction of bankruptcy using support vector machines: an application to bank bankruptcy.” Journal of Statistical Computation and Simulation, 83(8), pp. 1543-1555.
6. Ezzamel, M., Mar‐Molinero, C., & Beech, A. (1987). “On the distributional properties of financial ratios. ”Journal of Business Finance & Accounting, 14(4), pp. 463-481.
7. Fan, J. P., Wong, T. J., & Zhang, T. (2007). “Politically connected CEOs, corporate governance, and Post-IPO performance of China's newly partially privatized firms. ” Journal of financial economics, 84(2), pp. 330-357.
8. Feldman, R. (2013). “Techniques and applications for sentiment analysis. ”Communications of the ACM, 56(4), pp. 82-89.
9. Gentry, R. J., & Shen, W. (2010). “The relationship between accounting and market measures of” firm financial performance: How strong is it?Journal of managerial issues, pp. 514-530.
10. Hart, S. L. (1995). “A natural-resource-based view of the firm. ” Academy of management review, 20(4), pp. 986-1014.
11. Hinton, G. E., & Salakhutdinov, R. R. (2006). “Reducing the dimensionality of data with neural networks.” Science, 313, pp. 504-507.
12. Hinton, G. E., Osindero, S., & Teh, Y. W. “A fast learning algorithm for deep belief nets. ” Neural computation, 18(7), pp. 1527-1554.
13. Hitt, M. A., Hoskisson, R. E., & Ireland, R. D. (1994). “A mid-range theory of the interactive effects of international and product diversification on innovation and performance. ”Journal of management, 20(2), pp. 297-326.
14. Höglund, H. (2012). “ Detecting earnings management with neural networks. ”Expert Systems with applications, 39(10), pp. 9564-9570.
15. Judge, W. Q., & Douglas, T. J. (1998). “Performance implications of incorporating natural environmental issues into the strategic planning process: an empirical assessment.” Journal of management Studies, 35(2), pp. 241-262.
16. 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.
17. Liu, B. (2012). “Sentiment analysis and opinion mining.” Synthesis lectures on human language technologies, 5(1), pp. 1-167.
18. Mizik, N., & Jacobson, R. (2003). “Trading off between value creation and value appropriation: The financial implications of shifts in strategic emphasis.” Journal of Marketing, 67(1), pp. 63-76.
19. Pang, B., & Lee, L. (2008). “Opinion mining and sentiment analysis.” Foundations and Trends® in Information Retrieval, 2(1–2), pp. 1-135.
20. Peteraf, M. A. (1992). “A review of ghemawat's commitment: the dynamic of strategy.” Journal of Economics & Management Strategy, 1(3), pp. 575-582.
21. Pilkington, M., Ashta, A., & Sinapi, C. (2014). “A Perspective on the Views of Five Nobel Prize Winners on the Biggest Global Economic Problem.” Unpublished Manuscript.
22. Russell, J. A. (1980). “A circumplex model of affect. ”Journal of personality and social psychology, 39(6), pp. 1161-1162.
23. Russo, M. V., & Fouts, P. A. (1997). “A resource-based perspective on corporate environmental performance and profitability. ” Academy of management Journal, 40(3), pp. 534-559.
24. Saif, H., Fernandez, M., He, Y., & Alani, H. (2013). “Evaluation datasets for Twitter sentiment analysis: a survey and a new dataset, the STS-Gold.” In: 1st Interantional Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), 3 Dec 2013, Turin, Italy.
25. Sakai, T., & Haga, K. (2012). “Molecular genetic analysis of phototropism in Arabidopsis. ”Plant and Cell Physiology, 53(9), pp. 1517-1534.
26. Sheng, S., Zhou, K. Z., & Li, J. J. (2011). “The effects of business and political ties on firm performance: Evidence from China. ” Journal of Marketing, 75(1), pp. 1-15.
27. Siering, M., Clapham, B., Engel, O., & Gomber, P. (2017). “A taxonomy of financial market manipulations: establishing trust and market integrity in the financialized economy through automated fraud detection. ”Journal of Information Technology, 32(3), pp. 251-269.
28. Taboada, M., Brooke, J., Tofiloski, M., Voll, K., & Stede, M. (2011). “Lexicon-based methods for sentiment analysis. ”Computational linguistics, 37(2), pp. 267-307.
29. Venkatraman, N., & Ramanujam, V. (1986). “Measurement of business performance in strategy research: A comparison of approaches. ”Academy of management review, 11(4), pp. 801-814.
30. 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, 24(11), pp. 1957-1968.
31. Wei, W. L., Wu, C. H., & Lin, J. C. (2011). “ A regression approach to affective rating of Chinese words from ANEW. ” In Affective Computing and Intelligent Interaction (pp. 121-131). Springer, Berlin, Heidelberg.
32. Yu, L. C., Lee, L. H., Hao, S., Wang, J., He, Y., Hu, J. & Zhang, X. (2016). “Building Chinese affective resources in valence-arousal dimensions.” In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 540-545).