在過往有關於美國職業籃球 (National Basketball Association, NBA) 中的研究中，大多都以數據做為預測的基準來預測球場上的勝負以及球員的表現趨勢。然而，隨著近年來文本分析以及社群網路的蓬勃發展，社群平台上充斥著用戶對於喜愛事物的評論，這現象在籃球領域中也不例外。每個用戶針對球員的表現給予評論，字裡行間都傳達對於球員的評價。再者，對新秀進行後起之秀的預測對於球團在每年度的選秀會上選擇球員也是相當重要的依據。因此，在本研究中，我們透過收集Twitter上用戶對於2010-2017年中新秀的評論後，利用BERT將字轉為詞向量上的優點以及卷積神經網路 (Convolutional Neural Network, CNN) 對於局部重要特徵的提取，情感詞予以加權，並使用長短期記憶模型 (Long Short Term Memory, LSTM) 與注意力機制建立分類模型。在實驗中，本研究所提方法可以準確預測後起之秀。

Most of the literature about the National Basketball Association (NBA) used gameplay statistics to predict the result of a game and the players' performance. However, with the rapid development of social networking in recent years, social platforms are flooded with user comments on favorite things. This phenomenon is no exception in the basketball field. The users evaluate the players' performance through words. Furthermore, predicting rising stars for rookies is essential for the team to select players in the annual draft. Therefore, in this study, after collecting the comments on Twitter about the NBA rookies in 2010-2017, we used the BERT to convert words into word vectors. Then we adopted the Convolutional Neural Network (CNN) to extract critical local features. Sentimental words were weighted before the construction of the classification model. The long short-term memory (LSTM) and attention mechanism were used to construct the classification model. The proposed method accurately predicts whether a player will become a rising star in the experiments.

誌謝 I
摘要 II
Abstract III
目錄 IV
第一章 緒論 1
1.1研究背景與動機 1
1.2研究目的 3
第二章 文獻探討 4
2.1 籃球領域預測之相關文獻 4
2.2 後起之秀相關文獻 5
2.3 情感分析文獻 7
2.3.1 基於情感辭典的情感分析 8
2.3.2 基於機器學習技術的情感分析 9
2.3.3 基於深度學習技術的情感分析 10
2.4 詞嵌入模型-基於變換器的雙向編碼器表示技術(BERT) 12
2.5 預測模型 14
2.5.1支持向量機(Support Vector Machine，SVM) 14
2.5.2卷積神經網路 (Convolutional Neural Network，CNN) 15
2.5.3遞迴神經網路 (Recurrent Neural Network，RNN) 17
2.5.4長短期記憶模型 (Long Short-Term Memory，LSTM) 19
第三章 研究方法 21
3.1研究架構 21
3.2資料收集 22
3.3資料前處理 23
3.3.1斷詞 23
3.3.2去除停用詞 24
3.3.3詞嵌入 24
3.4情感詞權重計算 26
3.5訓練模型 27
3.5.1卷積層 27
3.5.2池化層 27
3.5.3 LSTM層 28
3.5.4 全連接層 29
第四章 實驗結果 30
第五章 結論 36
參考文獻 37

[1] Z. Mahmood, A. Daud, and R. A. Abbasi, "Using machine learning techniques for rising star prediction in basketball," Knowledge-Based Systems, vol. 211,2021. doi: 10.1016/j.knosys.2020.106506.
[2] D. Miljković, L. Gajić, A. Kovačević, and Z. Konjović, "The use of data mining for basketball matches outcomes prediction," in IEEE 8th international symposium on intelligent systems and informatics, pp. 309-312, 2010.
[3] W. Cai, D. Yu, Z. Wu, X. Du, and T. Zhou, "A hybrid ensemble learning framework for basketball outcomes prediction," Physica A: Statistical Mechanics and its Applications, vol. 528, 2019. doi: 10.1016/j.physa.2019.121461.
[4] G. Soliman, A. Misbah, and S. Eldawlatly, "Predicting all star player in the national basketball association using random forest," in 2017 Intelligent Systems Conference (IntelliSys), pp. 706-713, 2017.
[5] J. Shi and K. Song, "A discrete-time and finite-state Markov chain based in-play prediction model for NBA basketball matches," Communications in Statistics - Simulation and Computation, vol. 50, no. 11, pp. 3768-3776, 2019. doi: 10.1080/03610918.2019.1633351.
[6] M. A Gómez, S. J Ibáñez, I. Parejo, and P. Furley, "The use of classification and regression tree when classifying winning and losing basketball teams," Kinesiology, vol. 49, no. 1, pp. 47-56, 2017.
[7] P. F. Pai, L. H. ChangLiao, and K. P. Lin, "Analyzing basketball games by a support vector machines with decision tree model," Neural Computing and Applications, vol. 28, no. 12, pp. 4159-4167, 2016. doi: 10.1007/s00521-016-2321-9.
[8] F. Thabtah, L. Zhang, and N. Abdelhamid, "NBA Game Result Prediction Using Feature Analysis and Machine Learning," Annals of Data Science, vol. 6, no. 1, pp. 103-116, 2019, doi: 10.1007/s40745-018-00189-x.
[9] F. J. R. Ruiz and F. Perez Cruz, "A generative model for predicting outcomes in college basketball," Journal of Quantitative Analysis in Sports, vol. 11, no. 1, 2015. doi: 10.1515/jqas-2014-0055.
[10] F. Ding, Y. Liu, X. Chen, and F. Chen, "Rising Star Evaluation in Heterogeneous Social Network," IEEE Access, vol. 6, pp. 29436-29443, 2018. doi: 10.1109/access.2018.2812923.
[11] X. L. Li, C. S. Foo, K. L. Tew, and S. K. Ng, "Searching for rising stars in bibliography networks," in International conference on database systems for advanced applications, pp. 288-292, 2009.
[12] A. Daud, R. Abbasi, and F. Muhammad, "Finding Rising Stars in Social Networks," in Database Systems for Advanced Applications, (Lecture Notes in Computer Science, ch. Chapter 4, pp. 13-24, 2013.
[13] A. Daud, M. Ahmad, M. S. I. Malik, and D. Che, "Using machine learning techniques for rising star prediction in co-author network," Scientometrics, vol. 102, no. 2, pp. 1687-1711, 2014. doi: 10.1007/s11192-014-1455-8.
[14] Y. Nie, Y. Zhu, Q. Lin, S. Zhang, P. Shi, and Z. Niu, "Academic rising star prediction via scholar’s evaluation model and machine learning techniques," Scientometrics, vol. 120, no. 2, pp. 461-476, 2019. doi: 10.1007/s11192-019-03131-x.
[15] Z. Ning, Y. Liu, and X. Kong, "Social gene—A new method to find rising stars," in 2017 International Symposium on Networks, Computers and Communications (ISNCC), pp. 1-6, 2017.
[16] C. Zhang, C. Liu, L. Yu, Z. K. Zhang, and T. Zhou, "Identifying the academic rising stars via pairwise citation increment ranking," in Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference on Web and Big Data, pp. 475-483, 2017.
[17] M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, "Lexicon-based methods for sentiment analysis," Computational linguistics, vol. 37, no. 2, pp. 267-307, 2011.
[18] A. Jurek, M. D. Mulvenna, and Y. Bi, "Improved lexicon-based sentiment analysis for social media analytics," Security Informatics, vol. 4, no. 1, 2015. doi: 10.1186/s13388-015-0024-x.
[19] C. S. G. Khoo and S. B. Johnkhan, "Lexicon-based sentiment analysis: Comparative evaluation of six sentiment lexicons," Journal of Information Science, vol. 44, no. 4, pp. 491-511, 2017. doi: 10.1177/0165551517703514.
[20] S. Zhang, Z. Wei, Y. Wang, and T. Liao, "Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary," Future Generation Computer Systems, vol. 81, pp. 395-403, 2018. doi: 10.1016/j.future.2017.09.048.
[21] G. Xu, Z. Yu, H. Yao, F. Li, Y. Meng, and X. Wu, "Chinese Text Sentiment Analysis Based on Extended Sentiment Dictionary," IEEE Access, vol. 7, pp. 43749-43762, 2019. doi: 10.1109/access.2019.2907772.
[22] A. S. Manek, P. D. Shenoy, M. C. Mohan, and V. K. R, "Aspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier," World Wide Web, vol. 20, no. 2, pp. 135-154, 2016. doi: 10.1007/s11280-015-0381-x.
[23] J. Singh, G. Singh, and R. Singh, "Optimization of sentiment analysis using machine learning classifiers," Human-centric Computing and Information Sciences, vol. 7, no. 1, 2017. doi: 10.1186/s13673-017-0116-3.
[24] F. Huang, S. Zhang, J. Zhang, and G. Yu, "Multimodal learning for topic sentiment analysis in microblogging," Neurocomputing, vol. 253, pp. 144-153, 2017. doi: 10.1016/j.neucom.2016.10.086.
[25] L. Dey, S. Chakraborty, A. Biswas, B. Bose, and S. Tiwari, "Sentiment Analysis of Review Datasets Using Naïve Bayes‘ and K-NN Classifier," International Journal of Information Engineering and Electronic Business, vol. 8, no. 4, pp. 54-62, 2016. doi: 10.5815/ijieeb.2016.04.07.
[26] M. R. Huq, A. Ali, and A. Rahman, "Sentiment analysis on Twitter data using KNN and SVM," International Journal of Advanced Computer Science and Applications, vol. 8, no. 6, pp. 19-25, 2017.
[27] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, "Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning," IEEE Access, vol. 8, pp. 23522-23530, 2020. doi: 10.1109/access.2020.2969854.
[28] Z. Jianqiang, G. Xiaolin, and Z. Xuejun, "Deep Convolution Neural Networks for Twitter Sentiment Analysis," IEEE Access, vol. 6, pp. 23253-23260, 2018. doi: 10.1109/access.2017.2776930.
[29] D. Hyun, C. Park, M. C. Yang, I. Song, J. T. Lee, and H. Yu, "Target-aware convolutional neural network for target-level sentiment analysis," Information Sciences, vol. 491, pp. 166-178, 2019. doi: 10.1016/j.ins.2019.03.076.
[30] B. Shin, T. Lee, and J. D. Choi, "Lexicon integrated cnn models with attention for sentiment analysis," arXiv preprint arXiv:1610.06272, 2016.
[31] H. Chen, S. Li, P. Wu, N. Yi, S. Li, and X. Huang, "Fine-grained Sentiment Analysis of Chinese Reviews Using LSTM Network," Journal of Engineering Science and Technology Review, vol. 11, no. 1, pp. 174-179, 2018. doi: 10.25103/jestr.111.21.
[32] F. Hu, L. Li, Z. L. Zhang, J. Y. Wang, and X. F. Xu, "Emphasizing Essential Words for Sentiment Classification Based on Recurrent Neural Networks," Journal of Computer Science and Technology, vol. 32, no. 4, pp. 785-795, 2017. doi: 10.1007/s11390-017-1759-2.
[33] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding". arXiv preprint arXiv:1810.04805. 2018.
[34] 支持向量機示意圖, https://docs.opencv.org/2.4/doc/tutorials/ml/i ntroduction_to_svm/introduction_to_svm.html, retrieved on 2021/12/19
[35] 卷積神經網路架構示意圖, https://reurl.cc/AREv48 ,retrieved on 2021/12/23
[36] 遞迴神經網路架構示意圖, https://iter01.com/166306.html ,retrieved on 2021/12/23
[37] 遞迴神經網路應用示意圖, http://karpathy.github.io/2015/05/21/rnn-effectiveness/ retrieved on 2021/12/23
[38] 長短期記憶模型架構示意圖, https://colah.github.io/posts/2015-08-Understanding-LSTMs/ retrieved on 2021/12/28.
[39] 邏輯函數(S型函數)示意圖, https://en.wikipedia.org/wiki/File:Log istic-curve.svg, retrieved on 2021/12/23.
[40] NBA球員平均生涯壽命, https://nba.udn.com/nba/story/12608/4343695?utm_source=nbataiwan&utm_medium=fb , retrieved on 2022/07/20