臺灣博碩士論文加值系統

過去不同領域的研究經常將金融市場之財務指標和社群媒體間反映大眾情緒之評論拆分為兩涇渭分明的主題做探討。本研究使用主成分分析法將市場週轉率、資券餘額比、相對強弱指數、台指選擇權未平倉量比、批踢踢股票板之留言情緒五種指標建構為單項綜合投資人情緒指標，並分別探討各變數與新指標對於臺灣加權股價指數的資訊揭露能力。本研究結果發現，傳統財務指標、批踢踢股票版情緒與綜合情緒指標無論在迴歸或準確度的顯示均擁有不錯的預測效果，其中發現批踢踢股票版情緒於臺灣市場上之預測表現優於某些傳統財務指標，且不同時段的留言所攜帶之資訊揭露價值會影響情緒分數計算後於準確率上的表現。此外，本文在綜合情緒指標上得到落後一期負相關的結果，可能來自於投資人普遍存有樂觀偏誤現象，加上過度自信使得其在股市中的操作容易與報酬有反向關係，並同時在準確率上得到市場樂觀時的預測結果略優於悲觀時候。

In the past, research in different fields often divided the financial indicators of financial markets and the comments of public media on social sentiment into two distinct themes. In this study, principal component analysis was used to construct five indicators: turnover rate, financing / bearing ratio, relative strength index, put / call ratio, and sentiment of PTT stock board. And separately explore the information disclosure capabilities of each various variable and new indicator for Taiwan Capitalization Weighted Stock Index(TAIEX).
The results of this study found that traditional financial indicators, sentiment of PTT stock and comprehensive sentiment indicator have a good predictive effect in terms of regression or accuracy, and it is found that the performance of sentiment of PTT stock in the Taiwan market is better than some traditional financial indicators. Also, the value of the information disclosed in those indicators and messages held at different time periods will affect the performance of the emotional scores after calculation. In addition, this article has a negative correlation result in one lag phase of the comprehensive emotional index, which may come from the fact that investors generally have optimistic bias, and overconfidence makes its operation in the stock market easy to have an inverse relationship with remuneration, and in terms of accuracy, the market's optimistic forecast is slightly better than pessimistic.

摘要 i
ABSTRACT ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 3
1.3 論文架構 4
1.4 研究限制 5
第二章 文獻探討 6
2.1 電子佈告欄系統（Bulletin Board System，BBS） 6
2.1.1電子佈告欄系統的發展 6
2.1.2臺灣的接軌 7
2.2 情感分析（Sentiment Analysis） 8
2.2.1情感分析整理 9
2.2.2財務領域的應用 10
2.3 投資人情緒（Investor Sentiment） 12
2.3.1情緒指標的衡量 12
2.3.2投資人情緒與市場反應 13
第三章 研究設計與方法 16
3.1 投資人情緒指標 17
3.1.1資料來源 17
3.1.2研究變數 17
3.1.3單根檢定（Unit Root Test） 20
3.2批踢踢股票版情緒 21
3.2.1資料蒐集 21
3.2.2資料處理 22
3.2.3情感分析（Sentiment Analysis） 25
3.3綜合情緒指標 27
第四章 實證結果與分析 29
4.1 情緒指標之敘述統計與相關係數矩陣 29
4.2 單根檢定 31
4.3 主成分分析法建構綜合情緒指標 40
4.4 各情緒指標之迴歸分析與比較 42
4.4.1各情緒指標之分析檢定 42
4.4.2綜合情緒指標之分析檢定 47
4.4.3各情緒指標之比較 50
第五章 結論與建議 54
5.1結論 54
5.2建議 56
參考文獻 58

1.林秀奇，「BBS的發展與應用」，台北學生會訊，第7期，1994，第85-111頁。
2.陳文生、尹青海，「臺灣學術網路（TANet）現況簡介」，教育部電子計算機中心簡訊，第83卷，第11期，第3-15頁，1994。
3.趙國仁、陳年興，「TANET BBS的過去、現在與未來」，網路通訊雜誌，第51期， 1995，第74-81頁。
4.蔡珮，電子布告欄使用行為與社會臨場感研究：以台大計中BBS站為例，碩士論文，國立交通大學傳播研究所，新竹市，1995。
5.羅之綱，「網際網路電子布告欄發展近況」，視聽教育雙月刊，第40卷，第4期，1999，第19-24頁。
6.蘇侯彰，網際網路歷史的政經分析：美國與臺灣經驗，碩士論文，國立交通大學傳播所，新竹，2000。
7.周賓鳳、池祥萱、周冠男、龔怡霖，「行為財務學：文獻回顧與展望」，證券市場發展季刊，第14卷，第2期，2002，第1-48頁。
8.洪宗慶、蕭嘉農，「BBS, E-Mail, MSN, IM, ICQ, Skype網路人際關係」，網路社會學通訊期刊，第46期，2005。
9.周賓凰、張宇志、林美珍，「投資人情緒與股票報酬互動關係」，證券市場發展季刊，第19卷，第2期，第153-190頁，2007。
10.李紹良，十五萬人的BBS是如何煉成的：批踢踢實業坊技術演變歷程之研究（1995-2008），碩士論文，國立政治大學社會所，臺北，2012。
11.劉祐銘，臺灣大學生BBS流行與文化現象之研究，碩士論文，國立暨南國際大學課程教學與科技研究所，南投，2012。
12.郭俊桔、張育蓉，「使用情緒分析於圖書館使用者滿意度評估之研究」，圖書資訊學研究，第7卷，第2期，2013，第153-197頁。
13.林彥丞，PTT股票板討論對股市之影響，碩士論文，國立政治大學財務管理研究所，臺北，2016。
14.郝哲斌，散戶情緒與市場報酬互動之關係，碩士論文，國立中山大學財務管理學系研究所，高雄，2016。
15.劉清標、林筱鳳、陳宏榮，「股票報酬與情緒人投資之預測」，財金論文叢刊，第26期，2017，第1-18頁。
16.林思平，「網路八卦與真理政治： 批踢踢八卦板之閱聽人研究」，新聞學研究，第133期，2017，第135-188頁。
17.趙玉娟、陶振超，「政治網路口碑的情感分析：語意關連性之觀點」，傳播研究與實踐，第8卷，第2期，2018，第75-107頁。
18.盧奕叡，深度學習與情感分析應用於股價預測，碩士論文，國立交通大學資訊科學與工程研究所，新竹，2018。
19.Andrzej Romanowski and Michał Skuza, “Towards Predicting Stock Price Moves with Aid of Sentiment Analysis of Twitter Social Network Data and Big Data Processing Environment,” Advances in Business ICT: New Ideas from Ongoing Research, vol. 658, 2017, pp. 105-123.
20.Andrea Esuli and Fabrizio Sebastiani, “SENTIWORDNET：A Publicly Available Lexical Resource for Opinion Mining,” In Proceedings of the 5th Conference on Language Resources and Evaluation, Genoa, Italy, 2006, pp. 417-422.
21.Apoorv Agarwal, Boyi Xie, Ilia Vovsha, Owen Rambow, and Rebecca Passonneau, “Sentiment Analysis of Twitter Data,” Proceedings of the 11th LMS Workshop on Languages in Social Media, Portland, Oregon, 2011.
22.Brendan O’Connor, Ramnath Balasubramanyan, Bryan R. Routledge, and Noah A. Smith, “From Tweets to Polls：Linking Text Sentiment to Public Opinion Time Series,” Proceedings of the 4th International AAAI Conference on Weblogs and Social Media, Washington, DC, USA, 2010, pp. 122-129.
23.Chau, M. and Xu, J., “Mining Communities and Their Relationships in Blogs：A Study of Hate Groups,” International Journal of Human–Computer Studies, vol. 65, no. 1, 2007, pp. 57-70.
24.Chong Oh, and Olivia R Liu Sheng, “Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Future Stock Price Directional Movement,” Proceedings of the 32th International Conference on Information Systems, Shanghai, China, 2011.
25.Christos J. P. Moschovitis, Hilary Poole, Tami Schuyler, and Theresa M. Senft, History of the Internet：A Chronology, 1843 to the Present, ABC-CLIO, 1999.
26.Esuli, A. and Sebastiani, F., “Determining the semantic orientation of terms through gloss classification,” Proceedings of the 14th ACM International Conference on Information and knowledge management, Bremen, Germany, 2005, pp. 617-624.
27.G.Vinodhini, RM.Chandrasekaran, “Sentiment Analysis and Opinion Mining: A Survey,” International Journal of Advanced Research in Computer Science and Software Engineering, vol. 2, no. 6, 2012, pp. 282-292.
28.Gregory W. Brown and Michael T. Cliff, “Investor sentiment and the near-term stock market,” Journal of Empirical Finance, vol. 11, no. 4, 2004, pp. 1-27.
29.Haiqiang Chen, Terence Tai Leung Chong, and Yingni She, “A Principal Component Approach to Measuring Investor Sentiment in China,” Munich Personal RePEc Archive, no. 54150, 2014.
30.Jasmina Smailović, Miha Grčar, Nada Lavrač, and Martin Žnidaršič, “Stream-based active learning for sentiment analysis in the financial domain,” Information Sciences, vol. 285, no. 20, 2014, pp. 181-203.
31.Johan Bollen, Huina Mao, and XiaoJun Zeng, “Twitter mood predicts the stock market,” Journal of Computational Science,, vol. 2, no. 1, 2011, pp. 1-8.
32.John Naughton, A Brief History of the Future：Origins of the Internet, Orion Pub Co, 2000.
33.Kaiquan Xu, Stephen Shaoyi Liao, Jiexun Li, and Yuxia Song, “Mining comparative opinions from customer reviews for Competitive Intelligence,” Decision Support Systems, vol. 50, no. 4, 2011, pp. 743-754.
34.Kenneth L. Fisher and Meir Statman, “Investor Sentiment and Stock Returns,” Financial Analysts Journal, vol. 56, no. 2, 2000, pp. 16-23.
35.Ku, L.-W., and Chen, H.-H., “Mining opinions from the Web: Beyond relevance retrieval,” Journal of the American Society for Information Science and Technology, vol. 58, no. 12, 2007, pp. 1838-1850.
36.Kun Guo, Yi Sun, Xin Qian, “Can investor sentiment be used to predict the stock price? Dynamic analysis based on China stock market,” Physica A, vol. 469, 2017, pp. 390-396
37.Lei Zhang, Shuai Wang, and Bing Liu, “Deep Learning for Sentiment Analysis : A Survey,” Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, vol. 8, no. 4, 2018.
38.Malcolm Baker and Jeffrey Wurgler, “Investor Sentiment in the Stock Market,” Journal of Economic Perspectives, vol. 21, no. 2, 2007, pp. 129-151.
39.Martin, J., “Blogging for dollars,” Fortune Small Business, vol. 15, no. 10, 2005, pp. 88-92.
40.Rapp, D., “From bulletin boards to blogs,” Technology Review, vol. 106, no. 7, 2003.
41.Sehgal, V. and Song, C., “SOPS：Stock Prediction Using Web Sentiment,” Workshops Proceedings of the 7th IEEE International Conference on Data Mining, Omaha, Nebraska, 2007, pp. 21-26.
42.Sitaram Asur, Bernardo A. Huberman, "Predicting the future with social media," Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 01, Washington, DC, USA, 2010, pp.492-499.
43.Songbo Tan and Jin Zhang, “An empirical study of sentiment analysis for chinese documents,” Expert Systems with Applications, vol.34, no. 4, 2008, pp. 2622–2629.
44.Strapparava, C. and Valitutti, A., “WordNet affect：An affective extension of WordNet,” Proceedings of the 4th International Conference on Language Resources and Evaluation, 2004, pp. 1083-1086.
45.TaeHyuk Kim, Aejin Ha, “Investor Sentiment and Market Anomalies,” 23rd Australasian Finance and Banking Conference 2010 Paper, 2010.
46.Tatiana Bazzichelli, Networking：The Net as Artwork, Aarhus Universität, 2009.
47.Ting-Chun Peng and Chia-Chun Shih, “An Unsupervised Snippet-based Sentiment Classification Method for Chinese Unknown Phrases without using Reference Word Pairs,” 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Toronto, Canada, 2010.
48.Tuuli Toivonen, Sanna Mäki, and Risto Kalliola, “The riverscape of Western Amazonia – a quantitative approach to the fluvial biogeography of the region,” Journal of Biogeography, vol. 34, no. 8, 2007, pp. 1374-1387.
49.Wayne Y. Lee, Christine X. Jiang, and Daniel C. Indro, “Stock market volatility, excess returns, and the role of investor sentiment,” Journal of Banking & Finance, vol. 26, no. 12, 2002, pp. 2277-2299.