請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51642完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張勝凱(Sheng-Kai Chang) | |
| dc.contributor.author | Yen Wang | en |
| dc.contributor.author | 王嚴 | zh_TW |
| dc.date.accessioned | 2021-06-15T13:42:30Z | - |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-11 | |
| dc.identifier.citation | Blei, D. M., A. Y. Ng, and M. I. Jordan (2003), “Latent Dirichlet Allocation,” Journalof Machine Learning research, 3, 993-1022. Boukus, E. and J. Rosenberg (2006), “The Information Content of FOMC Minutes,” Available at SSRN: http://ssrn.com/abstract=922312. Devitt, A. and K. Ahmad (2007), “Sentiment Polarity Identification in Financial News:A cohesion-Based Approach,” In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic, pp. 984–991. Gadiraju, U., B. Fetahu, R. Kawase, P. Siehndel, and S. Dietze (2017), “Using Worker Self-Assessments for Competence-Based Pre-Selection in Crowdsourcing Microtasks,” ACM Transactions on Computer-Human Interaction, 24, 1–26. Huang, Y. L. and C. M. Kuan (2019), “Text Mining of the FOMC Minutes and Forecasts of Taiwan Economic Variables,” Taiwan Economic Review, 47, 363–391. Kang, C. H., H. J. Wang, and N. K. Chen (2017), “The Communication Effect of the Central Bank of Taiwan on Interest Rates and Exchange Rates,” Taiwan Economic Review, 45, 421–452. Kawamura, K., Y. Kobashi, M. Shizume, and K. Ueda (2019), “Strategic Central Bank Communication: Discourse Analysis of the Bank of Japan’s Monthly Report,” Journal of Economic Dynamics and Control, 100, 230–250. Koppel, M. and J. Schler (2006), “The Importance of Neutral Examples for Learning Sentiment,” Computational Intelligence, 22(2), 100–109. Li, X. D., H. R. Xie, L. Chen, J. P. Wang, and X. T. Deng (2014), “News Impact on Stock Price Return via Sentiment Analysis,” Knowledge-Based Systems, 69, 14–23. Lucca, D. O. and M. Emanuel (2015), “The Pre-FOMC Announcement Drift,” The Journal of Finance, 70(1), 329–371. Lucca, D. O. and F. Trebbi (2009), “Measuring Central Bank Communication: An Automated Approach with Application to FOMC Statements,” NBER Working Papers 15367, National Bureau of Economic Research, Inc. Nguyen, T. H. and K. Shirai (2015), “Topic Modeling Based Sentiment Analysis on Social Media for Stock Market Prediction,” Beijing, China, pp. 1354–1364. Association for Computational Linguistics. Pritchard, J. K., M. Stephens, and P. Donnelly (2000), “Inference of Population Structure Using Multilocus Genotype Data,” Genetics, 155(2), 945–959. Sadique, S., F. In, M. Veeraraghavan and Paul Wachtel (2013), “Soft Information and Economic Activity: Evidence from the Beige Book,” Journal of Macroeconomics, 37, 81-92. Shirota, Y., Y. Yano, T. Hashimoto, and T. Sakura (2015), “Monetary Policy Topic Extraction by Ysing LDA: Japanese Monetary Policy of the Second ABE Cabinet Term,” In 2015 IIAI 4th International Congress on Advanced Applied Informatics, pp. 8–13. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51642 | - |
| dc.description.abstract | 本文使用LDA主題模型，將中華民國中央銀行和美國聯邦公開市場委員會(Federal Open Market Committee，FOMC)所發布之官方文件，以每句話為單位，加入先驗知識分為不同經濟主題，再用情緒分析方法分為正面或負面情緒，並以情緒數量建立指標來預測台灣總體經濟變數。實證結果發現，在區分主題後，迴歸結果普遍比未區分主題來的好；而情緒分析方法，使用BERT來預測情緒的結果相較財務情緒字典方法來的合理。 | zh_TW |
| dc.description.abstract | This paper uses the Latent Dirichlet Allocation topic modeling to divide the official documents issued by the Central Bank of Taiwan and the Federal Open Market Committee(FOMC) into different topics with the prior economic knowledge, and then use sentiment analysis to divide them into positive or negative sentiment, and use the amount of sentiment to establish indicators to predict Taiwan's economic variable. The empirical results that after distinguishing topics, the regression results are generally better than those without distinguishing topics. The method of using BERT to predict sentiment is better than tranditional sentiment analysis. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T13:42:30Z (GMT). No. of bitstreams: 1 U0001-0908202016262700.pdf: 1918315 bytes, checksum: 44b4fb0b59da074f3d7a2786e9c1f926 (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 口試委員審定書………………………………………………………………ⅰ 誌謝……………………………………………………………………………ⅱ 中文摘要……………………………………………………………………ⅲ 英文摘要………………………………………………………………………ⅳ 目錄……………………………………………………………………………ⅴ 圖目錄………………………………………………………………………ⅵ 表目錄…………………………………………………………………………ⅶ 第一章 前言……………………………………………………………1 第二章 資料處理……………………………………………………………2 2.1 中央銀行理監事聯席會議………………………………………………2 2.2 FOMC……………………………………………………………………3 第三章 模型設定……………………………………………………………4 3.1 LDA主題模型………………………………………………………4 3.2 情緒分析……………………………………………………………7 第四章 實證分析……………………………………………………………9 4.1台灣央行理監事聯席會議之回歸分析……………………………9 4.2 FOMC之迴歸分析……………………………………………15 4.3 樣本外預測結果…………………………………………………18 第五章 結論…………………………………………………………………19 參考文獻……………………………………………………………………21 附錄一………………………………………………………………………23 附錄二………………………………………………………………………24 | |
| dc.language.iso | zh-TW | |
| dc.title | 以臺灣央行及美國聯邦銀行會議記錄預測台灣總體經濟指標：LDA主題模型及情緒分析的應用 | zh_TW |
| dc.title | Forecasts of Taiwan Economic Variables based on the Minutes of the Central Bank of Taiwan and the FOMC : Application of LDA topic model and sentiment analysis | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 王泓仁(Hung-Jen Wang),陳南光(Nan-Kuang Chen),王建強(Chien-Chiang Wang) | |
| dc.subject.keyword | 中華民國中央銀行,美國聯邦公開市場委員會,主題模型,情緒分析,BERT, | zh_TW |
| dc.subject.keyword | Central Bank of Taiwan,Faderal Open Market Committee,topic model,sentiment analysis,BERT, | en |
| dc.relation.page | 27 | |
| dc.identifier.doi | 10.6342/NTU202002720 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-11 | |
| dc.contributor.author-college | 社會科學院 | zh_TW |
| dc.contributor.author-dept | 經濟學研究所 | zh_TW |
| 顯示於系所單位： | 經濟學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0908202016262700.pdf 目前未授權公開取用 | 1.87 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。