請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83865
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 雷立芬(Li-Fen Lei) | |
dc.contributor.advisor | 雷立芬(Li-Fen Lei | lei@ntu.edu.tw | ), | |
dc.contributor.author | Fu-Hao Chen | en |
dc.contributor.author | 陳賦豪 | zh_TW |
dc.date.accessioned | 2023-03-19T21:21:14Z | - |
dc.date.copyright | 2022-08-31 | |
dc.date.issued | 2022 | |
dc.date.submitted | 2022-07-21 | |
dc.identifier.citation | Antweiler, W., and Frank, M. Z. (2004). Is all that talk just noise? The information content of internet stock message boards. The Journal of Finance, 59(3), 1259-1294. Baker, M., and Wurgler, J. (2006). Investor sentiment and the cross?section of stock returns. The Journal of Finance, 61(4), 1645-1680. Bollen, J., Mao, H., and Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1), 1-8. Brown, G. W. and Cliff, M. T. (2004). Investor sentiment and the near-term stock market. Journal of Empirical Finance, 11(1), 1-27. Cohen-Charash, Y., Scherbaum, C.A., Kammeyer-Mueller, J.D., and Staw, B. M.(2013). Mood and the market: Can press reports of investors' mood predict stock prices? PloS One, 8(8), e72031, DOI:10.1371/journal.pone.0072031 Ding, X., Zhang, Y., Liu, T., and Duan, J. (2015). Deep Learning for Event-Driven Stock Prediction. Proceeding of the Twenty-Fourth International Joint Conference on Artificail Intelligence, pp. 1-7. Dolan, R. J.(2002). Emotion, cognition, and behavior. Science, 298(5596), 1191-1194. Fama, E.(1970). Efficient Capital Markets: A Review of Theory and Empirical Work, Journal of Finance, 25(2), 383-417. Fisher, K. L. and M. Statman (2000). Investor Sentiment and Stock Returns. Financial Analysts Journal, 56(2),16-23. DOI:10.2469/faj.v56.n2.2340 Nofsinger, J. R.(2005). Social mood and financial economics. The Journal of Behavioral Fiannce, 6(3), 144-160. Oliveira, N., Cortez, P., and Areal, N. (2013). On the predictability of stock market behavior using stocktwits sentiment and posting volume. DOI:10.1007/978-3-642-40669-0_31. Schumaker, R.P., and Chen, H.(2009). Textual analysis of stock market prediction using breaking financial news: The AZFin Text System. ACM Transactions on Information Systems, 27(2), 1-19. DOI:10.1145/1462198.1462204 Zhou, Z., Zhao, J., and Xu, K. (2016). Can online emotions predict the stock market in China? arXiv preprint arXiv:1604.07529 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83865 | - |
dc.description.abstract | 本研究主要目的是分析投資人情緒對臺灣市值加權股價指數(TAIEX)的影響。研究使用股市爆料同學會作為分析的社群平台,樣本時間跨度為2021年1月4日至2022年4月29日,共186,902篇文章數據。本研究透過Python爬取了大盤討論版內的所有文章內容、讚數及留言數當作研究的數據集,並且為了分析文章的情緒,利用了結巴(Jieba) 套件將中立的文章內容斷詞以後,使用台大意見詞辭典(National Taiwan University Sentiment Dictionary, NTUSD)量化投資者的情緒,最後利用邏輯斯迴歸(Logistic Regression , LR)、支持向量機(Support vector machine, SVM)及隨機森林(Random forest, RF)等三個分類模型預測隔日開盤價、收盤價、日內最高價及日內最低價的漲跌。 實證結果顯示,投資人情緒對於開盤價漲跌的預測準確率達62.50%,對於收盤價漲跌的預測準確率達57.81%;但對於日內最高價及日內最低價無顯著預測效力。根據研究發現,建議投資人要改正有關會在討論版上發文的人都是小散戶沒有市場影響力的迷思,不可不理會市場情緒的走向,若要長期在市場中獲利,仍需要隨時密切關注市場情緒的波動以審慎調整手中的持股。 | zh_TW |
dc.description.abstract | The main purpose of this study is to analyze the impact of investor sentiment on the Taiwan Stock Exchange Capitalization Weighted Stock Index. This study selected Cmoney as the platform, and the historical stock market data was crawled from January 4th 2021 to April 29th 2022. In this time span, there are totally 186,902 articles. This study used Python to crawl all the contents, likes and comments as the data set. In order to analyze the sentiment of the article, Jieba was used to segment the neutral article, and then used NTUSD to quantify the investor sentiment. In the end, the study used logistic regression, support vector machine , and random forest to predict the fluctuation of the opening price, closing price, intra-day highest price, and intra-day lowest price. The results of this study reveals that the investor sentiment has an accuracy rate of 62.50% in predicting the opening price and 57.81% in closing price. However, it has no significant effect on the intra-day highest price and intra-day lowest price. It is suggested that investors should correct the myth that those who will post on the discussion board are retail investors without market influence, and should not ignore the trend of market sentiment. If investors want to make profits in the market for a long time, they still need to pay close attention to market sentiment and adjust their holdings appropriately. | en |
dc.description.provenance | Made available in DSpace on 2023-03-19T21:21:14Z (GMT). No. of bitstreams: 1 U0001-1306202216354800.pdf: 2136805 bytes, checksum: f25f5b67953b6d20b9069ebe08766039 (MD5) Previous issue date: 2022 | en |
dc.description.tableofcontents | 口試委員會審定書 i 致謝 ii 摘要 iii Abstract iv 圖目錄 vii 表目錄 viii 第一章 緒論 1 第一節 研究背景 1 第二節 研究目的 2 第二章 文獻回顧 5 第三章 研究方法 8 第一節 分析平台選擇 8 第二節 研究資料 10 第三節 資料預處理與分析方法 14 第四章 實證模型選擇 17 第一節 邏輯斯迴歸 17 第二節 支持向量機 19 第三節 隨機森林 22 第五章 實證結果與分析 25 第一節 模型一(正負面文章比例且用今日預測隔日交易日) 25 第二節 模型二(正負面文章比例、讚數及留言數且用今日預測隔日交易日) 38 第三節 模型三(正負面文章比例且用收盤預測隔日交易日) 48 第四節 模型四(正負面文章比例、讚數及留言數且用收盤預測隔日交易日) 57 第五節 分析結果與交叉驗證 67 第六章 結論 73 參考文獻 75 附錄 77 | |
dc.language.iso | zh-TW | |
dc.title | 利用網路投資人情緒預測臺灣股價 | zh_TW |
dc.title | Using Online Investor Sentiment to Predict Taiwan Stock Market Price | en |
dc.type | Thesis | |
dc.date.schoolyear | 110-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 楊豐安(Feng-An Yang),葉國俊(Kuo-chun Yeh) | |
dc.subject.keyword | 情緒分析,臺灣股市,機器學習, | zh_TW |
dc.subject.keyword | Sentiment Analysis,Taiwan Stock Market,Machine Learning, | en |
dc.relation.page | 102 | |
dc.identifier.doi | 10.6342/NTU202200933 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2022-07-22 | |
dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
dc.contributor.author-dept | 農業經濟學研究所 | zh_TW |
顯示於系所單位: | 農業經濟學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-1306202216354800.pdf 目前未授權公開取用 | 2.09 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。