跳到主要內容

臺灣博碩士論文加值系統

(100.28.227.63) 您好!臺灣時間:2024/06/15 01:04
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:陳怡安
研究生(外文):Chen, Yi-An
論文名稱:文本探勘技術之應用-發掘新聞情緒並探討其和恐慌指數之關聯性
論文名稱(外文):An Application of the Text Mining Technology- Extracting News Sentiment and Examining its Relationship with the Vix Index
指導教授:徐立群徐立群引用關係顏盟峯顏盟峯引用關係
指導教授(外文):Shu, Lih-ChyunYen, Meng-Feng
口試委員:王明隆蘇益生
口試日期:2017-07-10
學位類別:碩士
校院名稱:國立成功大學
系所名稱:財務金融研究所碩士在職專班
學門:商業及管理學門
學類:財務金融學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:中文
論文頁數:40
中文關鍵詞:恐慌指數文本探勘資料探勘
外文關鍵詞:Data MiningText MiningVix Index
相關次數:
  • 被引用被引用:0
  • 點閱點閱:14
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本研究旨在探討財經新聞情緒與恐慌指數間之關聯性。本研究收集財經新聞文本資料,透過文字探勘技術,與情緒詞庫進行比對,區分出正面及負面的情緒極性,量化成財經新聞情緒指數。並將上述三個財經新聞情緒指數分別與S&P500 波動率指數短期期貨ETN(iPath S&P 500 VIX Short-Term Futures Exchange-traded Notes)進行格蘭傑相關性檢定,檢定結果發現Opinion Lexicon情緒指數落後期數2至5期與S&P500波動率指數短期期貨ETN之報酬率具有領先落後關係。
  後將Opinion Lexicon情緒指數落後2至5期之變數帶入五個機器學習模型中,分別為梯度提升決策樹、隨機森林、類神經網路、羅吉斯回歸及支援向量機,將其S&P500 波動率指數短期期貨ETN之漲跌進行預測,預測結果發現在落後期數為五時,類神經網路預測結果表現最佳,故本研究採用該模型,進行投資交易策略。
  本研究將類神經網路預測結果帶入進行投資策略,並以買進持有及放空持有策略作為基準報酬率,實證結果顯示透過Opinion Lexicon情緒指數之類神經網路模型進行預測,以開盤價進行交易,具有可觀的正報酬表現。若以收盤價帶入投資策略,放空交易策略獲利空間明顯縮小,但買進交易策略可避免些許的投資損失。
The main purpose of research was to explore correlation between Financial News Sentiments and the Vix Index. The three financial news sentiment indexes composed of Opinion Lexicon, Financial Sentiment Dictionary and MPQA Opinion Corpus and the rate of iPath S&P 500 VIX Short-Term Futures Exchange-traded Notes(ETN) return were proceeded with Granger causality test, the results showed Opinion Lexicon provide statistically significant information about future values of iPath S&P 500 VIX Short-Term Futures ETN.
The study uses data mining techniques to predict the variations of iPath S&P 500 VIX Short-Term Futures ETN. Artificial neural network was adopted to the usages of investment strategy in this research due to its good result prediction.
The empirical results showed investors can obtain good benefits with opening price of transaction as applying artificial neural network of Opinion Lexicon sentiment index for prediction. If closing price was employed in investment strategy, buy-in trading strategy enabled to avoid some investment loss, the benefits margin significantly reduced as adopting short selling strategy.
摘要 I
Abstract II
誌謝 VI
目錄 VII
表目錄 VIII
圖目錄 IX
第一章緒論 1
第一節研究背景與動機 1
第二節研究目的 4
第三節研究架構 6
第二章文獻回顧 7
第一節資料探勘與文本挖掘 7
第二節恐慌指數相關文獻 9
第三節文本分析與金融指數之關聯性 11
第三章研究方法 13
第一節研究樣本與資料來源 13
第二節變數定義與衡量 14
第三節機器學習模型 22
第四章實證結果與分析 26
第一節敘述性統計 26
第二節格蘭傑因果檢定 29
第三節實證結果分析 32
第五章結論與建議 36
參考文獻 37
一、中文文獻
邱一薰,2005,類神經網路預測台灣 50 股價指數之研究,國立彰化師範大學資訊管理學系所碩士論文。
陳彥豪,2002,散戶與法人投資行為對股票報酬率與週轉率影響之探討--以台灣上市電子股為例,國立臺灣大學財務金融研究所碩士論文。
蔡依玲,2001,台灣股票市場報酬率之研究,國立成功大學統計系碩士論文。
羅國宏,1995,回饋式類神經網路之應用:以股票市場預測為例,國立中山大學 資訊管理研究所碩士論文。

二、英文文獻
Alexander, C. and D. Korovilas(2013), “Volatility Exchange-Traded Notes:Curse or Cure?”The Journal of Alternative Investments, Volume 16, pp.52-70.

Ahoniemi, K.(2006),“Modeling and Forecasting Implied Volatility an
Econometric Analysis of the VIX Index,”HECER Discussion Paper, pp.1-29.

Brooks, C. & M.C. Oozeer(2002), “Modeling the Implied Volatility of Options on Long Gilt Futures,” Journal of Business Finance & Accounting, Volume 29, pp.111-137.

Bollen, J., H. Mao & X. Zeng(2011),“Twitter Mood Predicts the Stock Market,”Journal of Computational Science, Volume 2,pp.1-8.

Blair, J., S. Poon & J. Taylor(2001),“Forecasting S&P 100 Volatility: The Incremental Information Content of Implied Volatilities and High Frequency Index Returns,” Journal of Econometrics, Volume 105, pp.5-26.

Brenner, M. & G.Dan(1989), “New Financial Instruments for Hedging Changes in Volatility,” Financial Analysts Journal, Volume 4, pp.61-65.

Brenner, M. & G. Dan (1993), “Hedging Volatility in Foreign Currencies,” The Journal of Derivatives, Volume 1, pp.53-59.

Bongiovanni, A., P. Vincentiis & E. Isaia(2016), “The VIX Index: Forecasting Power and Performance in a Risk Management Framework,” Journal of Financial Management, Markets and Institutions, Volume 4, pp.129-144.

Chen, M., J. Han & S. Philip(1996), “Data Mining: An Overview From a Database Perspective,”IEEE Transactions on Knowledge and Data
Engineering, Volume 8, pp.866-883.

Cao, Q., W. Duan & Q. Gan(2011),“Exploring Determinants of Voting for the Helpfulness of Online User Reviews: A Text Mining Approach,”Decision Support Systems, Volume 50, pp.511-521.

Choi, D., B. Ko, H. Kim & P. Kim(2014),“Text Analysis for Detecting
Terrorism-Related Articles on the Web,”Journal of Network and Computer Applications, Volume 38, pp.16-21.

Das, S. & M. Chen(2007), “Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web,” Management Science, Volume 53,pp.1375-1388.

Fayyad, U., G. Shapiro & P. Smyth(1996), “From Data Mining to Knowledge Discovery in Databases,” AI Magazine, Volume 17, pp.1-34.

Fayyad, U., G. Shapiro & P. Smyth(1996),“The KDD Process for Extracting Useful Knowledge from Volumes of Data,”Communications of the ACM, Volume 39,pp.27-34.

Engelberg, J.,A. Reed & M. Ringgenberg(2012), “How Are Shorts Informed?: Short Sellers, News, and Information Processing,”Journal of Financial Economics, Volume 105, pp.260-278.

Grob-Klubmann, A. & N. Hautsch(2011), “When Machines Read the News: Using Automated Text Analytics to Quantify High Frequency News-implied Market Reactions.”Journal of Empirical Finance, Volume 18, pp.321-340.

Hotho, A., A. Nurnberger & G. Paab(2005), “A Brief Survey of Text Mining,” Journal for Computational Linguistics and Language Technology, Volume 1, pp.19-62.

Hu, M. & B. Liu(2004), “Mining and Summarizing Customer Reviews,”Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.168-177.

Kearney, C. & S. Liu(2014),“Textual Sentiment in Finance: A Survey of Methods and Models,”International Review of Financial Analysis, Volume 33, pp.171-185.

Liu, B., M. Hu & J. Cheng(2005), “Opinion Observer: Analyzing and Comparing Opinions on the Web,” Proceedings of the 14th International World Wide Web Conference.

Mittermayer, M.(2004), “Forecasting Intraday Stock Price Trends with Text Mining Techniques,” Annual Hawaii International Conference on System Sciences (HICSS'04), Volume 3, pp.64-74.

Nagar A. & M. Hahsler (2012), “Using Text and Data Mining Techniques to Extract Stock Market Sentiment from Live News Streams,”International Conference on Computer Technology and Science, pp.91-95.

Nuno O., C. Paulo & A. Nelson(2013),“On the Predictability of Stock Market Behavior Using StockTwits Sentiment and Posting Volume,”Progress in Artificial Intelligence, Volume 81,pp.355-365.

Oconnor, B., R. Balasubramanyan & B. Routledge(2010), “From Tweets to Polls: Linking Text Sentiment to Public Opinion Time,” Conference Paper.

Tetlock, P., S. Maytal & S. Macskassy(2008),“More Than Words:
Quantifying Language to Measure Firms'Fundamentals,”The Journal of Finance, Volume3, pp.1437-1467.

Tseng, Y., C. Lin & Y. Lin(2007),“Text Mining Techniques for Patent Analysis,”Information Processing and Management, Volume 43, pp.1216- 1247, 2007.

Zhang, J., W. Hardle, C. Chen & E. Bommes(2016),“Distillation of News Flow Into Analysis of Stock Reactions,”Journal of Business & Economic Statistics, Volume 34, pp.547-563.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊