在泛政治化與社群媒體發達的情況下，各社群出現許多政治討論的影響者，左右輿論的走向。同時在台灣兩極化的政治背景下，討論框架容易陷入非綠及藍的二元討論框架，若影響者僅採取單一政治立場，可能會在社群中被貼標籤，進而喪失公信力。因此本研究想探討政治立場頻繁變化是否能讓自己不被定型，進而提升自身的社群影響力。我們透過深度學習BERT來分類預測文章作者的政黨傾向，並且觀察時間序列上的變化次數，並運用PageRank來衡量作者的網路中心性。結果證明政治立場變化次數越高，顯著提升影響者的網路中心性，但結果也無法證實立場變化次數會顯著影響追隨者忠誠度。最後希望本研究結果能讓影響者理解立場變化所帶來的好處及影響，若堅守單一的政治立場可能會喪失社群的影響力，也容易流於意識形態上的對立。

With the development of political discussions and social media, there are many influencers of political discussions in various communities, which influence the trend of public opinion. At the same time, in the context of Taiwan’s political polarization, the discussion framework tends to fall into a dualistic discussion. If an influencer adopts a single political stance, it may be labelled in the community and lose its credibility. Therefore, this research wants to explore whether frequent changes in political stances can prevent oneself from being stereotyped, thereby enhancing one's own social influence. We use deep learning BERT to classify and predict the party tendency of article authors, observe the number of changes in the time series, and use PageRank to measure network centrality. It turns out that the higher the number of changes in political stances, the greater the network centrality of influencers. In addition, this study cannot confirm that the number of changes in position will significantly affect the loyalty of followers. It is hoped that the results of this research will enable influencers to understand the benefits and effects of changes in political stance. If they adhere to a single political stance, they may lose the influence of the community and are likely to be limited to ideological opposition.

摘要 I
Abstract II
目錄 III
圖目錄 V
表目錄 VI
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究問題 3
第二章 文獻回顧 3
第一節 社群網路的影響者 4
第二節 立場變化者的社群影響 6
第三節 社會網路分析尋找網路中心點 9
第四節 文字探勘應用於政治領域 10
第五節 小結 13
第三章 研究方法 13
第一節 研究資料 13
第二節 政治傾向判斷 17
第三節 推文網絡分析 22
第四節 迴歸模型 23
第四章 分析結果 27
第一節 敘述性分析 27
第二節 迴歸分析 36
第五章 結論與建議 42
第一節 研究發現 42
第二節 研究貢獻與未來發展 42
第三節 研究限制 44
第六章 參考文獻 44

王泰俐（2013）。「臉書選舉」？ 2012 年台灣總統大選社群媒體對政治參與行為的影響。東吳政治學報，31(1)，頁1～52
林思平（2020）。純粹社群，掛釘社群與網絡個人主義：以批踢踢八卦板（PTT Gossiping）為例，資訊社會研究，（38），127-161。
董建宏&鄭力軒（2020）。從大數據分析看人口變遷與歷次大選變化。上網日期：2021年10月1日。取自：
https://www.cna.com.tw/news/aipl/202007080359.aspx
蔡佳青（2006）。八面玲瓏：台灣蘋果日報政治立場之初探。未出版之碩士論文，國立台北大學社會學系
龐雲黠＆苗偉山（2017）。意見領袖的結構極化研究：以新浪微博為例。傳播與社會學刊，(42)，59-90。
Baeza-Yates, R., & Saez-Trumper, D. (2015, August). Wisdom of the crowd or wisdom of a few? An analysis of users' content generation. In Proceedings of the 26th ACM conference on hypertext & social media, 69-74.
Bamakan, S. M. H., Nurgaliev, I., & Qu, Q. (2019). Opinion leader detection: A methodological review. Expert Systems with Applications, 115, 200-222.
Bimber, B., & Davis, R. (2003). Campaigning online: The Internet in US elections. Oxford University Press.
Carlson, T. N., & Settle, J. E. (2016). Political chameleons: An exploration of conformity in political discussions. Political Behavior, 38(4), 817-859.
Chandra, R., Saini, R., 2021. Biden vs Trump: Modeling US General Elections Using BERT Language Model. IEEE Access 9, 128494–128505.
Chen, H. T. (2018). Spiral of silence on social media and the moderating role of disagreement and publicness in the network: Analyzing expressive and withdrawal behaviors. New Media & Society, 20(10), 3917-3936.
Cui, Y., Che, W., Liu, T., Qin, B., Yang, Z., Wang, S., & Hu, G. (2019). Pre-training with whole word masking for chinese bert. arXiv preprint arXiv:1906.08101.
Day, D. V., & Schleicher, D. J. (2006). Self-monitoring at work: A motive-based perspective. Journal of Personality, 74(3), 685–713.
Deci, E.L. and Ryan, R.M. (2002), “Overview of self- determination theory: an organismic dialectical perspective”, Handbook of Self-Determination Research, The University of Rochester Press, Rochester, New York, NY, pp. 3-33.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Friedman, Elie, and Zohar Kampf. 2020. “‘To Thine Own Self Be True’: The Perceived Meanings and Functions of Political Consistency.” Language in Society 49 (1): 89–113.
Gao, M., Xiao, Z., Karahalios, K., Fu, W.-T., 2018. To Label or Not to Label. Proceedings of the ACM on Human-Computer Interaction 2, 1–16. doi:10.1145/3274324
Gupta, S., Bolden, S., Kachhadia, J., Korsunska, A., & Stromer-Galley, J. (2020, October). PoliBERT: Classifying political social media messages with BERT. In Social, Cultural and Behavioral Modeling (SBP-BRIMS 2020) conference. Washington, DC.
Jacomy, M., Venturini, T., Heymann, S., & Bastian, M. (2014). ForceAtlas2, a continuous graph layout algorithm for handy network visualization designed for the Gephi software. PloS one, 9(6), e98679.
Jain, L., & Katarya, R. (2018, February). A systematic survey of opinion leader in online social network. In 2018 International Conference on Soft-computing and Network Security (ICSNS) (pp. 1-5). IEEE.
Jones, E.E. and Davis, K.E. (1965), “From acts to dispositions the attribution process in person perception”, Advances in Experimental Social Psychology, Vol. 2 No. 1, pp. 219-266.
Jun, S. and Yi, J. (2020), "What makes followers loyal? The role of influencer interactivity in building influencer brand equity", Journal of Product & Brand Management, Vol. 29 No. 6, pp. 803-814.
Katz, E. (1957). The two-step flow of communication: An up-to-date report on an hypothesis. Public opinion quarterly, 21(1), 61-78.
Kiss, C., & Bichler, M. (2008). Identification of influencers—measuring influence in customer networks. Decision Support Systems, 46(1), 233-253.
Lazarsfeld, P. F., Berelson, B. R., & Gaudet, H. (1948). The people’s choice: How the voter makes up his mind in a presidential campaign. New York: Duell, Sloan & Pierce.
Luebke, S. M.. (2021). Political Authenticity: Conceptualization of a Popular Term. The International Journal of Press/politics, 26(3), 635–653.
Mislove, A., Marcon, M., Gummadi, K. P., Druschel, P., & Bhattacharjee, B. (2007, October). Measurement and analysis of online social networks. In Proceedings of the 7th ACM SIGCOMM conference on Internet measurement (pp. 29-42).
Nisbet, M. C., & Kotcher, J. E. (2009). A two-step flow of influence? Opinion-leader campaigns on climate change. Science Communication, 30(3), 328-354.
Noelle‐Neumann, E. (1974). The spiral of silence a theory of public opinion. Journal of communication, 24(2), 43-51.
O'Banion, S., & Birnbaum, L. (2013, August). Using explicit linguistic expressions of preference in social media to predict voting behavior. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (pp. 207-214).
Page, L., Brin, S., Motwani, R., & Winograd, T. (1999). The PageRank citation ranking: Bringing order to the web. Stanford InfoLab.
Riquelme, F., & González-Cantergiani, P. (2016). Measuring user influence on Twitter: A survey. Information processing & management, 52(5), 949-975.
Rose, P., & Kim, J. (2011). Self-monitoring, opinion leadership and opinion seeking: a sociomotivational approach. Current Psychology, 30(3), 203.
Strandberg, T., Sivén, D., Hall, L., Johansson, P., & Pärnamets, P. (2018). False beliefs and confabulation can lead to lasting changes in political attitudes. Journal of Experimental Psychology: General, 147(9), 1382.
Strandberg, T., Olson, J. A., Hall, L., Woods, A., & Johansson, P. (2020). Depolarizing American voters: Democrats and Republicans are equally susceptible to false attitude feedback. Plos one, 15(2), e0226799.
Shafiq, M. Z., Ilyas, M. U., Liu, A. X., & Radha, H. (2013). Identifying leaders and followers in online social networks. IEEE Journal on Selected Areas in Communications, 31(9), 618-628.
Snyder, M. (1974). Self-monitoring of expressive behavior. Journal of Personality and Social Psychology, 30(1), 434–461.
Snyder, M. (1987). Public appearances/private realities: The psychology of self-monitoring. New York: Freeman.
W. contributors. "PageRank," 9 September 2021.
https://zh.wikipedia.org/wiki/PageRank
Williams, H. T. P., Mcmurray, J. R., Kurz, T., & Hugo Lambert, F.. (2015). Network analysis reveals open forums and echo chambers in social media discussions of climate change. Global Environmental Change, 32, 126–138.
Wang, Austin Horng-En. 2019. “The Myth of Polarization among Taiwanese Voters: The Missing Middle.” Journal of East Asian Studies First View.