近年來深度學習技術獲得巨大關注與進步，並成功地應用於市場產品；以影像與聲音辨識為大宗，廣泛應用於不同領域。其中卷積神經網絡是最熱門的深度學習神經網路架構，最初在影像處理上取得了驚人的成果，之後其應用更擴及於各大領域。本論文提出使用卷積神經網絡(Convolutional Neural Network)來建立預測模型，並進行了兩項研究。第一部分基於與電影相關的網路關鍵資訊進行國內電影票房分析與預測，第二部分為風機大維護預測。台電於彰化濱海工業區有兩個風場，本論文使用兩個風場過去所收集的資料來進行風機大維護預測研究。實驗結果顯示出深度學習在預測上也能有不錯的效果。

In recent years, deep learning has received much public attention and made great progress technically; it has been successfully applied to the products in the marketplace, and it has been widely used in different fields for its capabilities in image and voice identification. Convolutional neural network (CNN) is popular deep-learning neural network architecture, and it has initially achieved impressive performance in image processing and can even be seen in various fields later. This paper proposes two studies based on Convolutional Neural Network to establish a predictive model. The first study analyzes and predicts the box office of Taiwan based on the key information related to the movie. The second study predicts the great maintenance of the wind turbines. Taipower has two wind farms located in Changhua Coastal Industrial Park. This paper uses data collected from two wind farms to do forecast research. The experimental results show that deep learning can also have good performance in forecasting.

審定書 i
誌謝 ii
中文摘要 iii
Abstract iv
Contents v
List of Figures vii
List of Tables viii
Chapter 1 Introduction 1
1.1 Introduction 1
1.2 Motivation 4
1.3 Contributions 5
1.4 Organization 6
Chapter 2 Background Review 7
2.1 Sentiment Analysis 7
2.2 Social Media 9
2.3 Movie box office 13
2.4 Condition monitoring of wind turbines 14
2.5 Related algorithm 15
2.5.1 Support Vector Machine 15
2.5.2 Convolutional Neural Network 16
2.5.3 Simple Linear Regression 17
2.5.4 Apriori Algorithm 18
Chapter 3 Proposed Method 20
3.1 Movie Box Office Forecasting 20
3.1.1 Data Collection 21
3.1.2 Data Preprocessing and Prediction Model Construction 22
3.2 Great Maintenance Time Forecasting 32
3.2.1 Data Preprocessing 33
3.2.2 Prediction Model Construction 41
Chapter 4 Experimental Results 43
4.1 Results of Movie Box Office Forecasting 43
4.2 Results of Great Maintenance Time Forecasting 46
Chapter 5 Conclusions 48
Reference 51

[1] Twitter, http://twitter.com.
[2] Facebook, http://facebook.com
[3] M. D. Conover, B. Gonçalves, J. Ratkiewicz, A. Flammini and F. Menczer, “Predicting the political alignment of twitter users,” in Proceedings of the International Conference on Social Computing, pp. 192-199, Boston, USA, Oct. 2011.
[4] Y. Liu, J. Huang, A. An and X. Yu, “ARSA: A sentiment-aware model for predicting sales performance using blogs,” in Proceedings of the ACM Special Interest Group on Information Retrieval, pp. 607-614, Amsterdam, The Netherlands, Jul. 2007.
[5] Epagogix, http://www.epagogix.com/
[6] A. R. Panaligan, and A. Chen, “Quantifying moviemagic with google search,” Google, 2013.
[7] Internet movie database, http://imdb.com.
[8] K. R. Apala, M. Jose, S. Motnam, C. C. Chan, K. J. Liszka and F. de Gregorio, “Prediction of movies box office performance using social media,” Advances in Social Networks Analysis and Mining (ASONAM), pp. 1209-1214, Niagara Falls, Canada, Aug. 2013.
[9] C. Cortes and V. Vapnik, “Support-vector networks,” Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[10] J. Han, M. Kamber and J. Pei, Data Mining: Concepts and Techniques, Third Edition, Morgan Kaufmann, 2006.
[11] B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up?: sentiment classification using machine learning techniques,” in Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, pp. 79-86, 2002.
[12] J. Erman, M. Arlitt, and A. Mahanti, “Traffic classification using clustering algorithms,” in Proceedings of the 2006 SIGCOMM workshop on Mining network data, pp. 281-286, 2006.
[13] A. Kyriakopoulou and T. Kalamboukis, “Text classification using clustering,” in Proceedings of The 17th European Conference on Machine Learning and the 10th European Conference on Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), pp. 28-38, 2006.
[14] N. Slonim, N. Friedman, and N. Tishby, “Unsupervised document classification using sequential information maximization,” in Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 129-136, 2002.
[15] A. Tumasjan, T. O. Sprenger, P. G. Sandner, and I. M. Welpe, “Predicting elections with twitter: What 140 characters reveal about political sentiment,” ICWSM, vol. 10, no. 1, pp. 178-185, 2010.
[16] T. Sakaki, M. Okazaki, and Y. Matsuo, “Earthquake shakes Twitter users: real-time event detection by social sensors,” in Proceedings of the 19th international conference on World wide web, pp. 851-860. 2010.
[17] M. Skoric, N. Poor, P. Achananuparp, E. P. Lim, and J. Jiang, “Tweets and votes: A study of the 2011 singapore general election.” HICSS, pp. 2583-2591, 2012.
[18] C. Williams, and G. Gulati, “What is a social network worth? Facebook and vote share in the 2008 presidential primaries,” American Political Science Association, 2008.
[19] B. O'Connor, R. Balasubramanyan, B. R Routledge, and N. A. Smith, “From tweets to polls: Linking text sentiment to public opinion time series,” ICWSM, vol. 11, pp. 122-129, 2010.
[20] J. Bollen, H. Mao, and X. Zeng, “Twitter mood predicts the stock market” Journal of computational science, vol. 2, no. 1, pp. 1-8, 2011.
[21] J. Ritterman, M. Osborne, and E. Klein, “Using prediction markets and Twitter to predict a swine flu pandemic,” In 1st international workshop on mining social media,vol. 9, pp. 9-17, 2009.
[22] N. UzZaman, R. Blanco, and M. Matthews, “TwitterPaul: Extracting and aggregating Twitter predictions,” arXiv preprint, 2012.
[23] E. Bothos, D. Apostolou, and G. Mentzas, “Using social media to predict future events with agent-based markets,” IEEE Intelligent Systems, vol. 25, no. 6, pp. 50-58, 2010.
[24] B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up?: sentiment classification using machine learning techniques,” In Proceedings of the ACL-02 conference on Empirical methods in natural language, vol. 10, pp. 79-86, 2002.
[25] A. Tumasjan, T. O. Sprenger, P. G. Sandner, and I. M. Welpe, “Predicting elections with twitter: What 140 characters reveal about political sentiment,” ICWSM, vol. 10, no. 1, pp. 178-185, 2010.
[26] P. T. Metaxas, E. Mustafaraj, and D. Gayo-Avello, “How (not) to predict elections.“ In Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), 2011 IEEE Third International Conference, pp. 165-171, 2011.
[27] “An In-Depth Look Inside the Twitter World,” http://www.sysomos.com/insidetwitter.
[28] D. Gayo Avello, P. T. Metaxas, and E. Mustafaraj, “Limits of electoral predictions using twitter,” in Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, 2011.
[29] B. J. Jansen, M. Zhang, K. Sobel, and A. Chowdury, “Twitter power: Tweets as electronic word of mouth,” Journal of the Association for Information Science and Technology, vol. 60, no. 11, pp. 2169-2188, 2009.
[30] S. Asur, B. A. Huberman, “Predicting the future with social media,” in Proceedings of the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, vol. 1, pp. 492-499, 2010.
[31] W. Zhang, and S. Skiena, “Improving movie gross prediction through news analysis,” In Web Intelligence and Intelligent Agent Technologies, vol. 1, pp. 301-304, 2009.
[32] M. Joshi, D. Das, K. Gimpel, and N. A. Smith, “Movie reviews and revenues: An experiment in text regression,” In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 293-296, 2010.
[33] R. Sharda, and D. Delen, “Predicting box-office success of motion pictures with neural networks,” Expert Systems with Applications, vol. 30 no. 2, pp. 243-254, 2006.
[34] B. Pang, and L. Lee, “Opinion mining and sentiment analysis,” Foundations and Trends in Information Retrieval, vol. 2, pp. 1-135, 2008.
[35] G. Mishne, and N. S. Glance, “Predicting Movie Sales from Blogger Sentiment,” In AAAI spring symposium: computational approaches to analyzing weblogs, pp. 155-158, 2006.
[36] P. Caselitz and J. Giebhardt, “Rotor condition monitoring for improved operational safety of offshore wind energy converters,” Journal of Solar Energy Engineering, vol. 127, no. 2, pp. 253-261, 2005.
[37] F. P. G. Márquez, A. M. Tobias, J. M. P. Pérez and M. Papaelias, “Condition monitoring of wind turbines: techniques and methods,” Renewable Energy, vol. 46, pp. 169-178, 2012.
[38] H. Muller, M. Poller, A. Basteck, M. Tilscher and J. Pfister, “Grid compatibility of variable speed wind turbines with directly coupled synchronous generator and hydro-dynamically controlled gearbox,” in Proceedings of Sixth International Workshop on Large-Scale Integration of Wind Power and Transmission Networks for Offshore Wind Farms, pp. 307-315, 2006.
[39] K. Schroeder, W. Ecke, J. Apitz, E. Lembke and G. Lenschow, “A fibre Bragg grating sensor system monitors operational load in a wind turbine rotor blade,” Measurement Science and Technology, vol. 17, no. 5, 2006.
[40] S. Soua, P. Van Lieshout, A. Perera, T. H. Gan, and B. Bridge, “Determination of the combined vibrational and acoustic emission signature of a wind turbine gearbox and generator shaft in service as a pre-requisite for effective condition monitoring,” Renewable Energy, vol. 51, pp. 175-181, 2013.
[41] E. Jasiūnienė, R. Raišutis, R. Šliteris, A. Voleišis and M. Jakas, “Ultrasonic NDT of wind turbine blades using contact pulse-echo immersion testing with moving water container,” Ultragarsas, vol. 63, no. 3, pp. 28-32, 2008.
[42] A. Kusiak, and A. Verma, “A data-mining approach to monitoring wind turbines,” IEEE Transactions on Sustainable Energy, vol. 3, no. 1, pp. 150-157, 2012.
[43] A. Kusiak, and A. Verma, “A data-driven approach for monitoring blade pitch faults in wind turbines,” IEEE Transactions on Sustainable Energy, vol. 2, no. 1, pp. 87-96, 2011.
[44] K. Kim, G. Parthasarathy, O. Uluyol, W. Foslien and S. Sheng and P. Fleming, “Use of SCADA data for failure detection in wind turbines,” in Proceedings of ASME 5th International Conference on Energy Sustainability, pp. 2071-2079, 2011.
[45] M. Schlechtingen, I. F. Santos and S. Achiche, “Using data-mining approaches for wind turbine power curve monitoring: a comparative study,” IEEE Transactions on Sustainable Energy, vol. 4, no. 3, pp. 671-679, 2013.
[46] R. Agrawal and R. Srikant, “Fast algorithms for mining association rules,” in Proceedings of 20th International Conference on Very Large Data Bases, pp. 487-499, 1994.
[47] PTT, https://www.ptt.cc
[48] 開眼電影網，http://atmovies.com.tw.
[49] 觸電網，http://truemovies.com
[50] J. Han and M. Kamber, “Data Mining:Concepts and Techniques,” 3rd ed. San Francisco: Morgan Kaufmann Publishers, pp. 112-114, 2011.
[51] 台灣最高電影票房，https://zh.wikipedia.org/wiki/台灣最高電影票房.
[52] L. P. Jing, H. K. Huang, and H.-B. Shi, “Improved feature selection approach TFIDF in text mining.” in Proceedings of International Conference on Machine Learning and Cybernetics, vol. 2, pp. 944-946, 2002.
[53] Y. Goldberg, and O. Levy, “word2vec explained: Deriving mikolov et al.'s negative-sampling word-embedding method,” arXiv preprint, 2014.
[54] Y. Kim, “Convolutional neural networks for sentence classification,” arXiv preprint, 2014.
[55] jieba, https://github.com/fxsjy/jieba.
[56] L. W. Ku and H. H. Chen, “Mining Opinions from the Web: Beyond Relevance Retrieval,” Journal of the American Society for Information Science and Technology, vol. 58, no. 12, pp. 1838-1850, 2007.
[57] Keras, https://github.com/keras-team/keras