從近年的社會事件，都可見新聞對於閱聽人的影響之重，由於新聞的產出會因為媒體隱含的政治立場以及記者撰文的觀點選擇，使得新聞只會呈現部份的事實。

根據過去的研究，學者將此現象稱為媒體框架(Media Frame)，而媒體框架會影響閱聽者的立場選擇和價值判斷。因著社群媒體的蓬勃發展，使得閱聽者會將自己在平台上看到且認同的文章分享出去，使得媒體框架的影響也加深，更甚形成同溫層，造成不同立場之間溝通更加困難。

過去對於新聞文本內容，多利用專家事先定義議題的框架，近年來也越來越多研究使用文件探勘技術，對於新聞文本進行自動化的分析。本研究試利用文件探勘技術，建立主題模型(Topic Model)，除了減少人為的參與，使系統能夠更加自動化，也降低經由專家定義框架額外產生的新框架。最後經由視覺化的方式呈現偏見之研究結果。

From recent social events, it can be seen that news has a serious impact on readers. Because the output of news will only show partial facts due to the implicit political slant of the media and the choice of opinions written by reporters.

According to past research, scholars call this phenomenon “media frame,” and the media frame affects the position choice and value judgment of the readers. Due to the vigorous development of social media, readers may share articles they read that are coherent with their thought and judgment, which will deepen the influence of the media frame to form a “echo chamber,” and create a greater communication gap between people in different points of view.

In the past, the content of news texts was mostly used by experts to define the frame of topics in advance. But in recent years, more and more researches used text mining techniques to automatically analyze news texts. In this research, we use text mining techniques to establish a topic model, which not only reduces human involvement, making the system more automated, but also reduces the additional generation of news frames defined by experts. Finally, the results of the research on bias are presented visually.

摘要 1
ABSTRACT 2
圖目錄 5
表目錄 6
第壹章、 緒論 7
1.1. 研究背景與動機 7
1.2. 研究目的 8
1.3. 論文架構 8
第貳章、 文獻探討 9
2.1 媒體偏見 9
2.2 自然語言處理 10
2.3 文件探勘 11
2.4 情緒分析 12
第參章、 研究方法與實驗設計 14
3.1 資料蒐集 15
3.2 前處理 16
3.3 涵蓋偏見分析 20
3.3.1 主題模型 20
3.3.2 相對涵蓋偏見分數 24
3.4 描述偏見分析 24
3.4.1 意見元素擷取 24
3.4.2 文本情緒分析 28
3.4.3 相對描述偏見分數 29
3.5 綜合分析與視覺化 30
3.6 偏見驗證 31
第肆章、 結果分析 32
4.1 研究資料 32
4.2 結果分析 33
4.2.1 涵蓋偏見結果分析 33
4.2.2 描述偏見結果分析 45
4.2.3 意見持有人分析 54
4.3 綜合分析與視覺化 55
4.4 偏見結果驗證 59
第伍章、 結論與未來研究 62
參考文獻 64
附錄 68
附錄A 實驗驗證之20篇新聞本文 68
附錄B 實驗驗證之測試介面 74

AlSumait, L., Barbará, D., & Domeniconi, C. (2008). On-line lda: Adaptive topic models for mining text streams with applications to topic detection and tracking. Paper presented at the 2008 eighth IEEE international conference on data mining.
Bethard, S., Yu, H., Thornton, A., Hatzivassiloglou, V., & Jurafsky, D. (2004). Automatic extraction of opinion propositions and their holders. Paper presented at the 2004 AAAI spring symposium on exploring attitude and affect in text.
Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: analyzing text with the natural language toolkit: " O'Reilly Media, Inc.".
Blei, D. M. (2012). Probabilistic topic models. Communications of the ACM, 55(4), 77-84.
Budak, C., Goel, S., & Rao, J. M. (2016). Fair and balanced? quantifying media bias through crowdsourced content analysis. Public Opinion Quarterly, 80(S1), 250-271.
Chiang, C.-F. (2007). Sources of media bias. Manuscript. Retrieved from http://homepage. ntu. edu. tw/~ chunfang/Bias. pdf on April, 24, 2012.
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. (2011). Natural language processing (almost) from scratch. Journal of machine learning research, 12(ARTICLE), 2493− 2537.
Covert, T. J. A., & Wasburn, P. C. (2007). Measuring media bias: A content analysis of Time and Newsweek coverage of domestic social issues, 1975–2000. Social science quarterly, 88(3), 690-706.
Cui, L., Meng, F., Shi, Y., Li, M., & Liu, A. (2014). A hierarchy method based on LDA and SVM for news classification. Paper presented at the 2014 IEEE international conference on data mining workshop.
D'Alessio, D., & Allen, M. (2000). Media bias in presidential elections: A meta‐analysis. Journal of communication, 50(4), 133-156.
De Fortuny, E. J., De Smedt, T., Martens, D., & Daelemans, W. (2012). Media coverage in times of political crisis: A text mining approach. Expert Systems with Applications, 39(14), 11616-11622.
Dixon, L., Li, J., Sorensen, J., Thain, N., & Vasserman, L. (2018). Measuring and mitigating unintended bias in text classification. Paper presented at the Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society.
Dong, Z., Dong, Q., & Hao, C. (2006). HowNet and the Computation of Meaning.
Doumit, S., & Minai, A. (2011). Online news media bias analysis using an LDA-NLP approach. Paper presented at the International Conference on Complex Systems.
Entman, R. M. (2007). Framing bias: Media in the distribution of power. Journal of communication, 57(1), 163-173.
Entman, R. M. (2010). Media framing biases and political power: Explaining slant in news of Campaign 2008. Journalism, 11(4), 389-408.
Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From data mining to knowledge discovery in databases. AI magazine, 17(3), 37-37.
Feldman, R. (2013). Techniques and applications for sentiment analysis. Communications of the ACM, 56(4), 82-89.
Florian, R., Ittycheriah, A., Jing, H., & Zhang, T. (2003). Named entity recognition through classifier combination. Paper presented at the Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003.
Goldberg, A. B., & Zhu, X. (2006). Seeing stars when there aren’t many stars: Graph-based semi-supervised learning for sentiment categorization. Paper presented at the Proceedings of TextGraphs: The first workshop on graph based methods for natural language processing.
Goldberg, Y., & Levy, O. (2014). word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. arXiv preprint arXiv:1402.3722.
Gunther, A. C., & Schmitt, K. (2004). Mapping boundaries of the hostile media effect. Journal of communication, 54(1), 55-70.
Hamborg, F., Donnay, K., & Gipp, B. (2019). Automated identification of media bias in news articles: an interdisciplinary literature review. International Journal on Digital Libraries, 20(4), 391-415.
Himelboim, I., McCreery, S., & Smith, M. (2013). Birds of a feather tweet together: Integrating network and content analyses to examine cross-ideology exposure on Twitter. Journal of computer-mediated communication, 18(2), 154-174.
Hu, X., Tang, J., Gao, H., & Liu, H. (2013). Unsupervised sentiment analysis with emotional signals. Paper presented at the Proceedings of the 22nd international conference on World Wide Web.
Kim, S.-M., & Hovy, E. (2004). Determining the sentiment of opinions. Paper presented at the COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics.
Kim, S.-M., & Hovy, E. (2006). Extracting opinions, opinion holders, and topics expressed in online news media text. Paper presented at the Proceedings of the Workshop on Sentiment and Subjectivity in Text.
Liu, B. (2010). Sentiment analysis and subjectivity. Handbook of natural language processing, 2(2010), 627-666.
Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), 1-167.
Loper, E., & Bird, S. (2002). NLTK: the natural language toolkit. arXiv preprint cs/0205028.
Ma, T., & Wan, X. (2010). Opinion target extraction in Chinese news comments. Paper presented at the Coling 2010: Posters.
Ma, W.-Y., & Chen, K.-J. (2003). Introduction to CKIP Chinese word segmentation system for the first international Chinese Word Segmentation Bakeoff. Paper presented at the Proceedings of the second SIGHAN workshop on Chinese language processing.
Manning, C., & Schutze, H. (1999). Foundations of statistical natural language processing: MIT press.
Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Bethard, S., & McClosky, D. (2014). The Stanford CoreNLP natural language processing toolkit. Paper presented at the Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations.
Miller, G. A. (1995). WordNet: a lexical database for English. Communications of the ACM, 38(11), 39-41.
Mimno, D., Wallach, H., Talley, E., Leenders, M., & McCallum, A. (2011). Optimizing semantic coherence in topic models. Paper presented at the Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing.
Newman, D., Chemudugunta, C., Smyth, P., & Steyvers, M. (2006). Analyzing entities and topics in news articles using statistical topic models. Paper presented at the International conference on intelligence and security informatics.
Park, S., Kang, S., Chung, S., & Song, J. (2009). NewsCube: delivering multiple aspects of news to mitigate media bias. Paper presented at the Proceedings of the SIGCHI conference on human factors in computing systems.
Park, S., Lee, S., & Song, J. (2010). Aspect-level news browsing: understanding news events from multiple viewpoints. Paper presented at the Proceedings of the 15th international conference on Intelligent user interfaces.
Peng, H., Cambria, E., & Hussain, A. (2017). A review of sentiment analysis research in Chinese language. Cognitive Computation, 9(4), 423-435.
Saez-Trumper, D., Castillo, C., & Lalmas, M. (2013). Social media news communities: gatekeeping, coverage, and statement bias. Paper presented at the Proceedings of the 22nd ACM international conference on Information & Knowledge Management.
Wan, X. (2008). Using bilingual knowledge and ensemble techniques for unsupervised Chinese sentiment analysis. Paper presented at the Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing.
Wang, S.-M., & Ku, L.-W. (2016). ANTUSD: A large Chinese sentiment dictionary. Paper presented at the Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16).
Wang, Y., He, W., Jiang, M., Huang, Y., & Qiu, P. (2020). CHOpinionMiner: An unsupervised system for Chinese opinion target extraction. Concurrency and Computation: Practice and Experience, 32(7), e5582.
Wu, X., Fang, L., Wang, P., & Yu, N. (2015). Performance of using LDA for Chinese news text classification. Paper presented at the 2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering (CCECE).
Zahid, A., Khan, M. N., Khan, A. L., Kamiran, F., & Nasir, B. (2020). Modeling, Quantifying and Visualizing Media Bias on Twitter. IEEE Access, 8, 81812-81821.
Zhou, G., & Su, J. (2002). Named entity recognition using an HMM-based chunk tagger. Paper presented at the Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics.