Responsive image
博碩士論文 etd-0612122-145651 詳細資訊
Title page for etd-0612122-145651
論文名稱
Title
基於BERT模型進行社群情緒與股價報酬預測之分析
Analysis of Social Media Sentiment and Stock Price Return Prediction Based on BERT Model
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
45
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2022-06-20
繳交日期
Date of Submission
2022-07-12
關鍵字
Keywords
社群媒體情緒、文字探勘、BERT模型、情緒分析、股價報酬預測、機器學習
Social Media Sentiment, Text Mining, Bert Model, Sentiment Analysis, Stock Price Return Prediction, Machine Learning
統計
Statistics
本論文已被瀏覽 275 次,被下載 0
The thesis/dissertation has been browsed 275 times, has been downloaded 0 times.
中文摘要
社群網路快速的發展,許多投資人不僅會使用社群媒體來發表自己對股票市場的看法,也將社群媒體視為獲取資訊的來源之一。本研究欲探討社群媒體情緒與股票市場之間的關係,以知名論壇PTT的STOCK版為研究對象,使用自然語言處理BERT (Bidirectional Encoder Representations form Transformers )模型建構社群媒體情緒指標,觀察BERT模型對於情緒分類的能力,並以XGBoost模型進行股價報酬預測,觀察社群媒體情緒指標對於股價報酬的預測能力。最後在考慮交易成本下,使用當沖交易策略,進行回測,探討社群媒體情緒是否能提升投資績效。研究結果發現(一) BERT模型具有良好的情緒分類能力。(二) 社群媒體情緒資料能提升模型對股價報酬的預測能力。(三) 社群媒體情緒資料能提升當沖交易策略報酬。
Abstract
With the rapid development of social networks, many investors not only use social media to express their views on the stock market, but also regard social media as one of the sources of information. This study intends to explore the relationship between social media sentiment and the stock market. Taking the STOCK board of the well-known forum PTT as the research object, we apply the natural language processing BERT (Bidirectional Encoder Representations form Transformers ) model to construct social media sentiment indicators, and observe the power of the BERT model to classify sentiments. We also use the XGBoost model to predict stock returns and observe the predictive capability of the social media sentiment indicators. Finally, under consideration of transaction costs, we construct the hedge trading strategy to explore whether social media sentiment can improve investment performance. The results of the study found that (1) the BERT model is good with multi-class sentiment classification tasks. (2) Social media sentiment indicators can improve the model’s performance to predict stock returns. (3) Social media sentiment indicators can improve the return of the hedge trading strategy.
目次 Table of Contents
論文審定書 i
摘要 ii
ABSTRACT iii
目錄 iv
圖次 vi
表次 vii
第一章緒論1
第一節 研究動機1
第二節 研究目的2
第三節 研究架構2
第二章 文獻回顧3
第一節 間接投資人情緒與股票市場關係3
第二節 直接投資人情緒與股票市場關係4
第三節 BERT模型於財經領域應用5
第三章 研究方法6
第一節 研究流程6
第二節 研究資料7
第三節 社群媒體留言處理7
第四節 BERT 模型10
第五節 留言情緒分數12
第六節 間接投資人情緒13
第七節 機器學習交易策略15
第四章 實證結果19
第一節 敘述統計19
第二節 BERT模型預測21
第三節 機器學習交易策略25
第五章 結論與建議33
第一節 結論33
第二節 研究建議34
參考文獻35

參考文獻 References
Baker, M., & Wurgler, J. (2000). The equity share in new issues and aggregate stock returns. The journal of Finance, 55(5), 2219-2257.
Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross‐section of stock returns. The journal of Finance, 61(4), 1645-1680.
Banz, R. W. (1981). The relationship between return and market value of common stocks. Journal of Financial Economics, 9(1), 3-18.
Barsky, R. B., & Sims, E. R. (2012). Information, animal spirits, and the meaning of innovations in consumer confidence. American Economic Review, 102(4), 1343-1377.
Bergman, N. K., & Roychowdhury, S. (2008). Investor sentiment and corporate disclosure. Journal of Accounting Research, 46(5), 1057-1083.
Chen, H., Chong, T. T.-L., & Duan, X. (2010). A principal-component approach to measuring investor sentiment. Quantitative Finance, 10(4), 339-347.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining,
Chong, T. T.-L., Cao, B., & Wong, W.-K. (2014). A new principal-component approach to measure the investor sentiment.
Colonescu, C. (2018). The effects of Donald Trump's Tweets on US financial and foreign exchange markets.
Cui, Y., Che, W., Liu, T., Qin, B., & Yang, Z. (2021). Pre-training with whole word masking for chinese bert. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29, 3504-3514.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Dunham, L. M., & Garcia, J. (2021). Measuring the effect of investor sentiment on financial distress. Managerial Finance.
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), 383-417.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
Hiew, J. Z. G., Huang, X., Mou, H., Li, D., Wu, Q., & Xu, Y. (2019). BERT-based financial sentiment index and LSTM-based stock return predictability. arXiv preprint arXiv:1906.09024.
Joubert, D., & Mason, A. (1992). Investment basics-XXV volume and the bull-bear cycle. Investment Analysts Journal, 21(35), 49-50.
Karpoff, J. M. (1987). The relation between price changes and trading volume: A survey. Journal of Financial and quantitative Analysis, 22(1), 109-126.
Kumari, J. (2019). Investor sentiment and stock market liquidity: Evidence from an emerging economy. Journal of Behavioral and Experimental Finance, 23, 166-180.
Li, M., Li, W., Wang, F., Jia, X., & Rui, G. (2021). Applying BERT to analyze investor sentiment in stock market. Neural Computing and Applications, 33(10), 4663-4676.
Nielsen, F. Å. (2011). A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. arXiv preprint arXiv:1103.2903.
Pontiff, J. (1995). Closed-end fund premia and returns implications for financial market equilibrium. Journal of Financial Economics, 37(3), 341-370.
Rozeff, M. S., & Kinney Jr, W. R. (1976). Capital market seasonality: The case of stock returns. Journal of Financial Economics, 3(4), 379-402.
Sousa, M. G., Sakiyama, K., de Souza Rodrigues, L., Moraes, P. H., Fernandes, E. R., & Matsubara, E. T. (2019). BERT for stock market sentiment analysis. 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI),
Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The journal of Finance, 62(3), 1139-1168.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Yin, L., Zhang, N., He, L., & Fang, W. (2016). A Study of Relationship between Investor Sentiment and Stock Price Based on Text Mining. 2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI),
余宛真. (2015). 投資人情緒, 公司治理與股票報酬之研究
周賓凰, 張宇志, & 林美珍. (2019). 投資人情緒與股票報酬互動關係. 證券市場發展季刊: 行為財務學特別專刊, 153.
郝哲斌. (2016). The interaction between retail sentiment and market return.
陳建宏, & 馬黛. (2018). 新聞輿情, 報酬與投資人交易行為.
謝委霖. (2015). 從財金新聞預測公司財報之營收走勢.

電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus:開放下載的時間 available 2025-07-12
校外 Off-campus:開放下載的時間 available 2025-07-12

您的 IP(校外) 位址是 44.211.26.178
現在時間是 2024-06-13
論文校外開放下載的時間是 2025-07-12

Your IP address is 44.211.26.178
The current date is 2024-06-13
This thesis will be available to you on 2025-07-12.

紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code