學術產出-Theses
Article View/Open
Publication Export
-
題名 應用情感分析在台灣立法院委員會會議發言
Application of Sentiment Analysis in the Committee Speeches of Taiwan Legislative Yuan Members作者 蔡佳穎
Tsai, Chia-Ying貢獻者 蔡炎龍<br>邱訪義
Tsai, Yen-Lung<br>Chiou, Fang-Yi
蔡佳穎
Tsai, Chia-Ying關鍵詞 自然語言處理
BERT
情感分析
部門聲譽
議會發言
NLP
BERT
Sentiment Analysis
Agency Reputation
Parliamentary Speeches日期 2024 上傳時間 1-Mar-2024 13:59:38 (UTC+8) 摘要 Transformer的架構在自然語言處理領域中具有重要的貢獻,其自注意機制和多頭注意力機制的設計使模型能夠更好地捕捉句子中的語義資訊。例如,BERT和GPT等模型均採用了Transformer的架構。在本文中,我們採用了 BERT模型,針對台灣立法委員在委員會會議中對各個部門的質詢發言進行情感分析。透過對這些發言的分類,我們統整了不同情感的數量後,再去計算負面情感的比率,以深入分析不同部門在四年期間聲譽的變化情況。
The Transformer architecture has made significant contributions to the field of natural language processing, allowing models to more effectively capture semantic information within sentences through its self-attention and multi-head attention mechanisms, such as BERT and GPT. In this study, we utilized the BERT model to perform sentiment analysis on parliamentary speeches by Taiwanese legislators during committee meetings. Our specific focus was on interpellations directed at various government agencies. By categorizing these speeches, we aggregated the quantities of different sentiments to calculate the negative ratio, offering an in-depth analysis of the changing reputation of different agencies over a four-year period.參考文獻 [1] L Jason Anastasopoulos and Andrew B Whitford. Machine learning for public administration research, with application to organizational reputation. Journal of Public Administration Research and Theory, 29(3):491–510, 2019. [2] Luca Bellodi. A dynamic measure of bureaucratic reputation: New data for new theory. American Journal of Political Science, 67(4):880–897, 2023. [3] Leo Breiman. Random forests. Machine learning, 45:5–32, 2001. [4] Daniel P Carpenter and George A Krause. Reputation and public administration. Public administration review, 72(1):26–32, 2012. [5] Kakia Chatsiou and Slava Jankin Mikhaylov. Deep learning for political science. arXiv preprint arXiv:2005.06540, 2020. [6] Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning, 20:273–297, 1995. [7] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre- training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. [8] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. [9] Niels D Goet. Measuring polarization with text analysis: Evidence from the uk house of commons, 1811–2015. Political Analysis, 27(4):518–539, 2019. [10] Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, et al. Conformer: Convolution- augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100, 2020. [11] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [12] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019. [13] Andrew McCallum, Kamal Nigam, et al. A comparison of event models for naive bayes text classification. In AAAI-98 workshop on learning for text categorization, volume 752, pages 41–48. Madison, WI, 1998. [14] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013. [15] Tomas Mikolov, Quoc V Le, and Ilya Sutskever. Exploiting similarities among languages for machine translation (2013). arXiv preprint arXiv:1309.4168, 2022. [16] Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, and Kristina Miler. Tea party in the house: A hierarchical ideal point topic model and its application to republican legislators in the 112th congress. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1438–1448, 2015. [17] Sjors Overman, Madalina Busuioc, and Matthew Wood. A multidimensional reputation barometer for public agencies: A validated instrument. Public Administration Review, 80(3):415–425, 2020. [18] Jeffrey Pennington, Richard Socher, and Christopher D Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543, 2014. [19] Andrew Peterson and Arthur Spirling. Classification accuracy as a substantive quantity of interest: Measuring polarization in westminster systems. Political Analysis, 26(1):120– 128, 2018. [20] Daniel Preoţiuc-Pietro, Ye Liu, Daniel Hopkins, and Lyle Ungar. Beyond binary labels: Political ideology prediction of twitter users. In Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers), pages 729–740, 2017. [21] XinRong.word2vecparameterlearningexplained.arXivpreprintarXiv:1411.2738,2014. [22] David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. Learning representations by back-propagating errors. nature, 323(6088):533–536, 1986. [23] James Sanders, Giulio Lisi, and Cheryl Schonhardt-Bailey. Themes and topics in parliamentary oversight hearings: A new direction in textual data analysis. Statistics, Politics and Policy, 8(2):153–194, 2017. [24] Alper Kursat Uysal. An improved global feature selection scheme for text classification. Expert systems with Applications, 43:82–92, 2016. [25] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. [26] QianZhang,HanLu,HasimSak,AnshumanTripathi,ErikMcDermott,StephenKoo,and Shankar Kumar. Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7829–7833. IEEE, 2020. 描述 碩士
國立政治大學
應用數學系
110751002資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110751002 資料類型 thesis dc.contributor.advisor 蔡炎龍<br>邱訪義 zh_TW dc.contributor.advisor Tsai, Yen-Lung<br>Chiou, Fang-Yi en_US dc.contributor.author (Authors) 蔡佳穎 zh_TW dc.contributor.author (Authors) Tsai, Chia-Ying en_US dc.creator (作者) 蔡佳穎 zh_TW dc.creator (作者) Tsai, Chia-Ying en_US dc.date (日期) 2024 en_US dc.date.accessioned 1-Mar-2024 13:59:38 (UTC+8) - dc.date.available 1-Mar-2024 13:59:38 (UTC+8) - dc.date.issued (上傳時間) 1-Mar-2024 13:59:38 (UTC+8) - dc.identifier (Other Identifiers) G0110751002 en_US dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150225 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 應用數學系 zh_TW dc.description (描述) 110751002 zh_TW dc.description.abstract (摘要) Transformer的架構在自然語言處理領域中具有重要的貢獻,其自注意機制和多頭注意力機制的設計使模型能夠更好地捕捉句子中的語義資訊。例如,BERT和GPT等模型均採用了Transformer的架構。在本文中,我們採用了 BERT模型,針對台灣立法委員在委員會會議中對各個部門的質詢發言進行情感分析。透過對這些發言的分類,我們統整了不同情感的數量後,再去計算負面情感的比率,以深入分析不同部門在四年期間聲譽的變化情況。 zh_TW dc.description.abstract (摘要) The Transformer architecture has made significant contributions to the field of natural language processing, allowing models to more effectively capture semantic information within sentences through its self-attention and multi-head attention mechanisms, such as BERT and GPT. In this study, we utilized the BERT model to perform sentiment analysis on parliamentary speeches by Taiwanese legislators during committee meetings. Our specific focus was on interpellations directed at various government agencies. By categorizing these speeches, we aggregated the quantities of different sentiments to calculate the negative ratio, offering an in-depth analysis of the changing reputation of different agencies over a four-year period. en_US dc.description.tableofcontents 致謝 i Acknowledgments ii 中文摘要 iii Abstract iv Contents v List of Tables vii List of Figures viii 1 Introduction 1 2 Literature Review 4 2.1 DeepLearning 4 2.1.1 NeuralNetwork 4 2.1.2 ActivationFunction 6 2.1.3 LossFunction 7 2.1.4 Optimization 9 2.2 WordEmbeddings 10 2.2.1 Word2Vec 10 2.2.2 GloVe 12 2.3 LLM 14 2.3.1 Attention 15 2.3.2 Transformer 17 2.3.3 BERT 18 3 Experiments 19 3.1 DataDescription 21 3.2 Result 25 4 Conclusion 33 Appendix A 34 Bibliography 35 zh_TW dc.format.extent 4593933 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110751002 en_US dc.subject (關鍵詞) 自然語言處理 zh_TW dc.subject (關鍵詞) BERT zh_TW dc.subject (關鍵詞) 情感分析 zh_TW dc.subject (關鍵詞) 部門聲譽 zh_TW dc.subject (關鍵詞) 議會發言 zh_TW dc.subject (關鍵詞) NLP en_US dc.subject (關鍵詞) BERT en_US dc.subject (關鍵詞) Sentiment Analysis en_US dc.subject (關鍵詞) Agency Reputation en_US dc.subject (關鍵詞) Parliamentary Speeches en_US dc.title (題名) 應用情感分析在台灣立法院委員會會議發言 zh_TW dc.title (題名) Application of Sentiment Analysis in the Committee Speeches of Taiwan Legislative Yuan Members en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] L Jason Anastasopoulos and Andrew B Whitford. Machine learning for public administration research, with application to organizational reputation. Journal of Public Administration Research and Theory, 29(3):491–510, 2019. [2] Luca Bellodi. A dynamic measure of bureaucratic reputation: New data for new theory. American Journal of Political Science, 67(4):880–897, 2023. [3] Leo Breiman. Random forests. Machine learning, 45:5–32, 2001. [4] Daniel P Carpenter and George A Krause. Reputation and public administration. Public administration review, 72(1):26–32, 2012. [5] Kakia Chatsiou and Slava Jankin Mikhaylov. Deep learning for political science. arXiv preprint arXiv:2005.06540, 2020. [6] Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning, 20:273–297, 1995. [7] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre- training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. [8] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020. [9] Niels D Goet. Measuring polarization with text analysis: Evidence from the uk house of commons, 1811–2015. Political Analysis, 27(4):518–539, 2019. [10] Anmol Gulati, James Qin, Chung-Cheng Chiu, Niki Parmar, Yu Zhang, Jiahui Yu, Wei Han, Shibo Wang, Zhengdong Zhang, Yonghui Wu, et al. Conformer: Convolution- augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100, 2020. [11] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [12] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019. [13] Andrew McCallum, Kamal Nigam, et al. A comparison of event models for naive bayes text classification. In AAAI-98 workshop on learning for text categorization, volume 752, pages 41–48. Madison, WI, 1998. [14] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013. [15] Tomas Mikolov, Quoc V Le, and Ilya Sutskever. Exploiting similarities among languages for machine translation (2013). arXiv preprint arXiv:1309.4168, 2022. [16] Viet-An Nguyen, Jordan Boyd-Graber, Philip Resnik, and Kristina Miler. Tea party in the house: A hierarchical ideal point topic model and its application to republican legislators in the 112th congress. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1438–1448, 2015. [17] Sjors Overman, Madalina Busuioc, and Matthew Wood. A multidimensional reputation barometer for public agencies: A validated instrument. Public Administration Review, 80(3):415–425, 2020. [18] Jeffrey Pennington, Richard Socher, and Christopher D Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543, 2014. [19] Andrew Peterson and Arthur Spirling. Classification accuracy as a substantive quantity of interest: Measuring polarization in westminster systems. Political Analysis, 26(1):120– 128, 2018. [20] Daniel Preoţiuc-Pietro, Ye Liu, Daniel Hopkins, and Lyle Ungar. Beyond binary labels: Political ideology prediction of twitter users. In Proceedings of the 55th annual meeting of the association for computational linguistics (volume 1: long papers), pages 729–740, 2017. [21] XinRong.word2vecparameterlearningexplained.arXivpreprintarXiv:1411.2738,2014. [22] David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. Learning representations by back-propagating errors. nature, 323(6088):533–536, 1986. [23] James Sanders, Giulio Lisi, and Cheryl Schonhardt-Bailey. Themes and topics in parliamentary oversight hearings: A new direction in textual data analysis. Statistics, Politics and Policy, 8(2):153–194, 2017. [24] Alper Kursat Uysal. An improved global feature selection scheme for text classification. Expert systems with Applications, 43:82–92, 2016. [25] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. [26] QianZhang,HanLu,HasimSak,AnshumanTripathi,ErikMcDermott,StephenKoo,and Shankar Kumar. Transformer transducer: A streamable speech recognition model with transformer encoders and rnn-t loss. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7829–7833. IEEE, 2020. zh_TW