學術產出-Theses
Article View/Open
Publication Export
-
題名 以情緒分析量化新聞資料探討新台幣匯率市場效率性之研究
The Efficiency of USD/TW FX Market -----Quantifying News Materials with Sentiment Analysis作者 張邑齊
Chang, Yi-Chi貢獻者 林信助
張邑齊
Chang, Yi-Chi關鍵詞 外匯市場
文字探勘
GARCH模型
FX Market
Sentiment analysis
GARCH model日期 2019 上傳時間 5-Sep-2019 15:39:25 (UTC+8) 摘要 本研究之主要目的為透過文字探勘中的情緒分析方法以ANTUSD情緒詞庫量化新聞資料,利用新聞情緒分數衡量市場情緒,結合OLS與GARCH(1,1)建立迴歸模型,探討新台幣匯率市場之效率性。本研究分別使用: 1. 匯率相關之財經新聞全文 2.匯率相關新聞中匯銀主管針對匯率走勢所發表之談話內容 兩種新聞資料,作為計算新聞情緒分數的樣本,並比較上述兩種新聞資料何者對於匯率之走勢有較佳的解釋能力。根據本研究之實證結果,以匯率相關之財經新聞全文計算之情緒分數作為變數之模型表現較佳。在樣本期間2018/01/01至2019/03/20內,以量化之新聞情緒分數衡量之市場情緒對於新台幣兌美元之匯率是存在解釋力的,且匯率的走勢的波動也會受到新聞情緒的變異所影響,代表新台幣匯率市場違反效率市場假說。
This study uses quantified news materials as a measure of market sentiment in order to test the efficiency of USD/NTD FX market. By quantifying FX rate related news materials with ANTUSD sentiment lexicon, news sentiment can be transformed into numeric variable that can be used to build up econometric model. Base on the result of the GARCH(1,1) model implemented in this thesis, within 2018/01/01~2019/03/20, news sentiment significantly affects the USD/NTW exchange rate. Moreover, the variance of the news sentiment also affects the volatility of the USD/NTW exchange rate. Hence, according to the results of the model, this research concludes that USD/NTW FX market doesn’t follow the efficient market hypothesis.參考文獻 中文文獻1. 張興華 (2013)。從央行干預新聞分析台灣央行外匯市場干預與台幣匯率之關係。證券市場發展季刊,25,95-112。2. 李建慧、黃信棠 (2011)。市場交易訊息對匯率之影響。亞太經濟管理評論,15,71-88。3. 陳裕崧、謝邦昌、李勝輝、陳郁婷 (2014)。運用文字探勘與資料採礦技術建立匯率預測模型 -以人民幣兌新台幣為例 。數據分析,9,133-1464. 柯秀欣 (2018)。台灣央行外匯市場干預對台美匯率之影響–媒體資料之應用。 經濟論文叢刊,46,297-322。英文文獻5. Barberis, N., Shleifer, A., and Vishny, R. (1998), “A model of investor sentiment,” Journal of Financial Economics, 49 , 307-343.6. Brouwer, Y. (2017), “News Sentiment and Foreign Exchange Markets.” (Master’s thesis, Erasmus University Rotterdam)7. Engel, C. and West, K. D. (2005), “Exchange Rates and Fundamentals,” Journal of Political Economy, 113, 485-517.8. Evans, M. D. D., and Lyons, R. K. (2002), “Order Flow and Exchange Rate Dynamics.,” Journal of Political Economy, 1109. Fama, E. (1970), “American Finance Association Efficient Capital Markets: A Review of Theory and Empirical,” Journal of Finance, 25, 383-417.10. French, K. R. and Roll, R. (1986), “Stock Return Variances: The Arrival of Information and Reaction of Traders.,” Journal of Financial Economics, 17, 5-26.11. Hodrick, R. J. and Prescott, E. C. (1997), “Postwar U.S. Business Cycles : An Empirical Investigation.,” 29, 1-16.12. Komariah, K. S., Machbub, C., and Prihatmanto, A. S. (2016), “A Study of Efficient Market Hypothesis to Predict Exchange Rate Trends Using Sentiment Analysis of Twitter Data.,” Journal of Korea Multimedia Society, 19, 1107-1115.13. Ku, L. W., Ho, H. W., & Chen, H. H. (2009). “Opinion mining and relationship discovery using CopeOpi opinion analysis system.,” Journal of the American Society for Information Science and Technology, 60(7), 1486-1503.14. Meese, R. A., and Rogoff, k. (1983), “Empirical Exchange Rate Models of The Seventies.,” Journal of International Economics, 14, 3-24. 描述 碩士
國立政治大學
國際經營與貿易學系
106351024資料來源 http://thesis.lib.nccu.edu.tw/record/#G0106351024 資料類型 thesis dc.contributor.advisor 林信助 zh_TW dc.contributor.author (Authors) 張邑齊 zh_TW dc.contributor.author (Authors) Chang, Yi-Chi en_US dc.creator (作者) 張邑齊 zh_TW dc.creator (作者) Chang, Yi-Chi en_US dc.date (日期) 2019 en_US dc.date.accessioned 5-Sep-2019 15:39:25 (UTC+8) - dc.date.available 5-Sep-2019 15:39:25 (UTC+8) - dc.date.issued (上傳時間) 5-Sep-2019 15:39:25 (UTC+8) - dc.identifier (Other Identifiers) G0106351024 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/125501 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 國際經營與貿易學系 zh_TW dc.description (描述) 106351024 zh_TW dc.description.abstract (摘要) 本研究之主要目的為透過文字探勘中的情緒分析方法以ANTUSD情緒詞庫量化新聞資料,利用新聞情緒分數衡量市場情緒,結合OLS與GARCH(1,1)建立迴歸模型,探討新台幣匯率市場之效率性。本研究分別使用: 1. 匯率相關之財經新聞全文 2.匯率相關新聞中匯銀主管針對匯率走勢所發表之談話內容 兩種新聞資料,作為計算新聞情緒分數的樣本,並比較上述兩種新聞資料何者對於匯率之走勢有較佳的解釋能力。根據本研究之實證結果,以匯率相關之財經新聞全文計算之情緒分數作為變數之模型表現較佳。在樣本期間2018/01/01至2019/03/20內,以量化之新聞情緒分數衡量之市場情緒對於新台幣兌美元之匯率是存在解釋力的,且匯率的走勢的波動也會受到新聞情緒的變異所影響,代表新台幣匯率市場違反效率市場假說。 zh_TW dc.description.abstract (摘要) This study uses quantified news materials as a measure of market sentiment in order to test the efficiency of USD/NTD FX market. By quantifying FX rate related news materials with ANTUSD sentiment lexicon, news sentiment can be transformed into numeric variable that can be used to build up econometric model. Base on the result of the GARCH(1,1) model implemented in this thesis, within 2018/01/01~2019/03/20, news sentiment significantly affects the USD/NTW exchange rate. Moreover, the variance of the news sentiment also affects the volatility of the USD/NTW exchange rate. Hence, according to the results of the model, this research concludes that USD/NTW FX market doesn’t follow the efficient market hypothesis. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機 1第二節 研究方法與資料範圍 2第三節 本文架構 3第二章 文獻探討 4第一節 市場微結構 4第二節 效率市場假說 5第三節 文字探勘在匯率研究中的應用 6第三章 研究方法 8第一節 文字探勘 8第二節 資料搜集 9第三節 新聞情緒分析 9第四節 模型變數 12第五節 變數檢驗與模型設定 13第四章 實證結果 18第一節 新聞資料的敘述性統計分析 18第二節 以匯率新聞全文資料衡量市場情緒之實證分析 20第三節 以匯銀主管談話衡量市場情緒之實證分析 23第五章 結論與檢討 26第一節 研究結論 26第二節 研究檢討 27參考文獻 29 zh_TW dc.format.extent 1044117 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0106351024 en_US dc.subject (關鍵詞) 外匯市場 zh_TW dc.subject (關鍵詞) 文字探勘 zh_TW dc.subject (關鍵詞) GARCH模型 zh_TW dc.subject (關鍵詞) FX Market en_US dc.subject (關鍵詞) Sentiment analysis en_US dc.subject (關鍵詞) GARCH model en_US dc.title (題名) 以情緒分析量化新聞資料探討新台幣匯率市場效率性之研究 zh_TW dc.title (題名) The Efficiency of USD/TW FX Market -----Quantifying News Materials with Sentiment Analysis en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 中文文獻1. 張興華 (2013)。從央行干預新聞分析台灣央行外匯市場干預與台幣匯率之關係。證券市場發展季刊,25,95-112。2. 李建慧、黃信棠 (2011)。市場交易訊息對匯率之影響。亞太經濟管理評論,15,71-88。3. 陳裕崧、謝邦昌、李勝輝、陳郁婷 (2014)。運用文字探勘與資料採礦技術建立匯率預測模型 -以人民幣兌新台幣為例 。數據分析,9,133-1464. 柯秀欣 (2018)。台灣央行外匯市場干預對台美匯率之影響–媒體資料之應用。 經濟論文叢刊,46,297-322。英文文獻5. Barberis, N., Shleifer, A., and Vishny, R. (1998), “A model of investor sentiment,” Journal of Financial Economics, 49 , 307-343.6. Brouwer, Y. (2017), “News Sentiment and Foreign Exchange Markets.” (Master’s thesis, Erasmus University Rotterdam)7. Engel, C. and West, K. D. (2005), “Exchange Rates and Fundamentals,” Journal of Political Economy, 113, 485-517.8. Evans, M. D. D., and Lyons, R. K. (2002), “Order Flow and Exchange Rate Dynamics.,” Journal of Political Economy, 1109. Fama, E. (1970), “American Finance Association Efficient Capital Markets: A Review of Theory and Empirical,” Journal of Finance, 25, 383-417.10. French, K. R. and Roll, R. (1986), “Stock Return Variances: The Arrival of Information and Reaction of Traders.,” Journal of Financial Economics, 17, 5-26.11. Hodrick, R. J. and Prescott, E. C. (1997), “Postwar U.S. Business Cycles : An Empirical Investigation.,” 29, 1-16.12. Komariah, K. S., Machbub, C., and Prihatmanto, A. S. (2016), “A Study of Efficient Market Hypothesis to Predict Exchange Rate Trends Using Sentiment Analysis of Twitter Data.,” Journal of Korea Multimedia Society, 19, 1107-1115.13. Ku, L. W., Ho, H. W., & Chen, H. H. (2009). “Opinion mining and relationship discovery using CopeOpi opinion analysis system.,” Journal of the American Society for Information Science and Technology, 60(7), 1486-1503.14. Meese, R. A., and Rogoff, k. (1983), “Empirical Exchange Rate Models of The Seventies.,” Journal of International Economics, 14, 3-24. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU201900777 en_US