臺灣博碩士論文加值系統

近年來，隨著無線網路與行動裝置的迅速發展，投資者愈發容易從多來源網頁資料取得各種資料。雖有眾多的網頁資料來源，但投資者經常受單一來源的資料影響而產生資訊不一致狀況進而誤判趨勢。此外，因為網頁資料的特性複雜且多為非結構化資料，故如何從各種網頁資料來源處理並取得客觀的資訊是一個具挑戰的任務。為解決此問題，本論文提出一個遺傳為基礎的多來源屬性最佳化演算法，旨在從多來源網頁資料找出有效的分類屬性用以建立預測模型分析多來源網頁資料與股市之間的關係及影響。所提方法首先針對三個網頁資料來源，包含：財經新聞、社群媒體與經濟指標，進行資料前處理取得可能的特徵屬性。接著，利用二元編碼方式進行特徵屬性的編碼。在評估函數上，則利用兩個因子計算染色體適合度值，分別為模型準確度與屬性來源多元性。演化後，最佳的分類屬性集合將輸出並用來建立預測模型。運用此預測模型，我們可以提供一個相對客觀的趨勢判斷結果給使用者參考使用。

In recent years, with the rapid development of wireless networks and mobile devices, it has become easier for investors to get various information from multi-source web data. Although there are many sources of web data, investors are often influenced by a single source of data, as a results, inconsistent information and misjudging trends are occurred. In addition, since the characteristics of web data are complex and most of them are unstructured data, how to process and obtain objective information from multi-source web data is a challenging task. In order to solve this problem, this paper proposes a genetic-based multi-source attribute optimization algorithm, which aims to find effective classification attributes from multi-source web data to construct a prediction model to analyze the relationship and influence between multi-source web data and the stock market. The proposed approach first targets three web data sources, including: financial news, social media and economic indicators, and performs data preprocessing to obtain possible classification attributes. Then, the binary encoding schema is utilized to encode those attributes. As to the fitness function, two factors that are accuracy of model and diversity of attribute sources are used to calculate fitness value of a chromosome. After evolution, the best set of classification attributes is output and used to build a prediction model. Using the built prediction model, we expect to provide a relatively objective trend judgment result for users' reference.

目錄
中文摘要 ------------------------------------------------------------------------------------- i
英文摘要 ------------------------------------------------------------------------------------- ii
誌謝 -------------------------------------------------------------------------------------- iii
目錄 ------------------------------------------------------------------------------------- iv
表目錄 ------------------------------------------------------------------------------------- v
圖目錄 ------------------------------------------------------------------------------------- vi
符號說明 ------------------------------------------------------------------------------------- vii
第一章 緒論------------------------------------------------------------------------- 1
第一節 研究背景與研究動機------------------------------------------------- 1
第二節 研究目的與論文貢獻------------------------------------------------- 2
第三節 閱讀指引---------------------------------------------------------------- 3
第二章 文獻探討------------------------------------------------------------------- 4
第一節 單來源網頁資料於股市分析---------------------------------------- 4
第二節 多來源網頁資料於股市分析---------------------------------------- 6
第三節 背景知識---------------------------------------------------------------- 8
第三章 研究方法------------------------------------------------------------------- 15
第一節 問題定義---------------------------------------------------------------- 15
第二節 研究架構圖------------------------------------------------------------- 15
第三節 所提方法-MsWDSMAO---------------------------------------------- 16
第四節 MsWDSMAO虛擬碼與流程範例---------------------------------- 23
第四章 分析與結果---------------------------------------------------------32
第一節 實驗數據集---------------------------------------------------------32
第二節 實驗環境與參數設定--------------------------------------------------32
第三節 實驗設計與評估-----------------------------------------------------33
第五章 討論與改進---------------------------------------------------------------- 37
參考文獻 ------------------------------------------------------------------------------- 38

參考文獻

1.Barber, B. M. and Odean, T. (2008). All That Glitters: The Effect of attention and news on the buying behavior of individual and institutional investors. Review of Financial Studies, Vol. 21, No. 2, pp. 785-818.
2.Chen, W. F., & Ku, L. W. (2018). Introduction to CSentiPackage Tools for Chinese Sentiment Analysis”, Journal of Library & Information Science, 44 (1), 24-41.
3.Costola, M., Hinz, O., Nofer, M., & Pelizzon, L. (2023). Machine learning sentiment analysis, COVID-19 news and stock market reactions. Research in International Business and Finance, 64, 101881.
4.Duan, J., Ding, X., Zhang, Y., & Liu, T. (2019). TEND: A target-dependent representation learning framework for news document. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(12), 2313-2325.
5.Giachanou, A., & Crestani, F. (2016). Like it or not: A survey of twitter sentiment analysis methods, ACM Computing Surveys (CSUR), 49(2), 1-41.
6.Golberg, D. E. (1989). Genetic algorithms in search, optimization, and machine learning. Addion wesley, 1989(102), 36.
7.Gu, C., & Kurov, A. (2020). Informational role of social media: Evidence from Twitter sentiment. Journal of Banking & Finance, 121, 10596.
8.Heston, S. L., & Sinha, N. R. (2017). News vs. sentiment: Predicting stock returns from news stories. Financial Analysts Journal, 73(3), 67-83.
9.Holland, J. H. (1992). Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press.
10.Jiao, P., Veiga, A., & Walther, A. (2020). Social media, news media and the stock market. Journal of Economic Behavior & Organization, 176, 63-90.
11.Kanungsukkasem, N., & Leelanupab, T. (2019). Financial latent Dirichlet allocation (FinLDA): Feature extraction in text and data mining for financial time series prediction. IEEE Access, 7, 71645-71664.
12.Lee, H. S. (2020). Exploring the initial impact of COVID-19 sentiment on US stock market using big data. Sustainability, 12(16), 6648.
13.Mao, H., Counts, S., & Bollen, J. (2011). Predicting financial markets: Comparing survey, news, twitter and search engine data. arXiv, preprint arXiv:1112.1051.
14.Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv, arXiv :1301.3781v3.
15.Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality. International Conference on Neural Information Processing Systems, Vol. 2 Pages 3111–3119. 2013.
16.Mohan, S., Mullapudi, S., Sammeta, S., Vijayvergia, P., & Anastasiu, D. C. (2019) Stock price prediction using news sentiment analysis”, In 2019 IEEE fifth international conference on big data computing service and applications (BigDataService) (pp. 205-208). IEEE.
17.Ren, J., Long, J., and Xu, Z. (2019). Financial news recommendation based on graph embeddings. Decision Support Systems, Vol. 125, pp. 1-11.
18.Sawhney, R., Wadhwa, A., Agarwal, S., & Shah, R. (2021). FAST: Financial news and tweet based time aware network for stock trading. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, Main Volume (pp. 2164-2175).
19.Schumaker, R. P., Zhang, Y., Huang, C. N., & Heston, H. (2012). Evaluating sentiment in financial news articles. Decision Support Systems, 53(3), 458-464.
20.Shah, D., Isah, H., & Zulkernine, F. (2018). Predicting the effects of news sentiments on the stock market. In 2018 IEEE International Conference on Big Data (Big Data), pp. 4705-4708, IEEE.
21.Simoes, C., Neves, R., & Horta, N. (2017). Using sentiment from twitter optimized by genetic algorithms to predict the stock market. In 2017 IEEE Congress on Evolutionary Computation (CEC), pp. 1303-1310, IEEE.
22.Song, C., Wang, X. K., Cheng, P. F., Wang, J. Q., & Li, L. (2020). SACPC: A framework based on probabilistic linguistic terms for short text sentiment analysis. Knowledge-Based Systems, 194, 105572.
23.Sprenger, T. O., Sandner, P. G., Tumasjan, A., & Welpe, I. M. (2014). News or noise? Using Twitter to identify and understand company‐specific news flow. Journal of Business Finance & Accounting, 41(7-8), 791-830.
24.Tetlock, P. C. (2013). Giving content to investor sentiment: The role of media in the stock market. The Journal of finance, 62(3), 1139-1168.
25.Wu, C., Wu, F., Wu, S., Yuan, Z., Liu, J., & Huang, Y. (2019). Semi-supervised dimensional sentiment analysis with variational autoencoder. Knowledge-Based Systems, 165, 30-39.
26.Yu, L. C., Wu, J. L., Chang, P. C., & Chu, H. S. (2013). Using a contextual entropy model to expand emotion words and their intensity for the sentiment classification of stock market news. Knowledge-Based Systems, 41, 89-97.