在21世紀後真相(post-trust)的時代，社群媒體的蓬勃以及網路的發展，人人都是訊息製造者與傳播者，讓網路訊息難以被驗證、控管，未控管的假訊息嚴重將影響政策推動，甚至是造成人員死亡，假新聞的辨識與防止傳播將是重要的議題，本論文主要探討假新聞的特徵，以及特徵標記工具對於假新聞辨識正確率之影響，並進一步分析假新聞的特徵對於分享之間的關係，本論文從台灣事實查核中心(TFC)以及衛生福利部食品藥物管理署(FDA)闢謠專區蒐集健康、生活文章約百篇，篩選出其中21篇不需圖片輔助閱讀，且在系統標記上能顯著呈現，以此作為文章篩選依據，並建立一套輔助判讀假新聞的系統，利用BERT演算法進行實體辨識(Named Entity Recognition, NER)，主要用於提取文章的專有名詞，透過實體辨識(NER)將本論文的文章進行人事時地物的分析與提取，建立標記功能，並透過LIWC辭典進行情緒詞的分析，最後使用問卷調查方法取得閱聽者對於閱讀假新聞的特徵值數據，進一步使用虛假指數等了解特徵值影響閱聽者判斷假新聞的重要因素。研究結果顯示，如提供標記功能提示，將影響閱聽者選擇，認為具有人事時地物資訊，具有事實內容，其次，研究也顯示，文章是否具有轉載資訊以及是否有反駁網站，對於閱聽者判斷是否為假的重要依據。最後，將問卷結果進行虛假指數分析後，結論為虛擬指數越高，假新聞辨識正確率越高，分享率越低。

In the post-truth era of the 21st century, with the flourishing of social media and the ubiquity of the internet, everyone has become a creator and disseminator of information. This has made it difficult to verify and manage online information, and unchecked false information can seriously impact policy-making and even lead to casualties. Recognizing and preventing the spread of fake news has become an important issue. This thesis mainly investigates the characteristics of fake news and the impact of tagging tools on the accuracy of fake news identification. Furthermore, it analyzes the relationship between the characteristics of fake news and sharing. The thesis collects articles in the health and lifestyle categories from the Taiwan Fact-Checking Center (TFC) and the Food and Drug Administration (FDA) rumor-refuting section, with the criterion of articles readable without the need for image assistance. It establishes a system to assist in reading fake news, utilizing the BERT algorithm for Named Entity Recognition (NER) to analyze and extract entities, and creating a tagging function. Emotional word analysis is conducted using the LIWC dictionary, and survey methods are employed to obtain data on readers' characteristic values when reading fake news. Subsequently, the Fake News Index is used to understand the important factors influencing readers' judgments of fake news. The results indicate that tagging prompts affect readers' choices, leading them to perceive articles as factual. Moreover, whether articles have been reproduced or countered is shown to be an important basis for readers to judge their authenticity. Finally, through the analysis of survey results with the Fake News Index, the conclusion is drawn that the higher the Fake News Index, the higher the accuracy of fake news identification and the lower the sharing rate.

摘要 i
Abtract ii
致謝 iii
第一章 緒論 1
1.1研究背景 1
1.2研究動機與目的 3
1.3研究限制 5
1.4名詞解釋 5
第二章 文獻探討 6
2.1媒體識讀 6
2.1.1媒體發展 6
2.1.2假新聞 7
2.2文字探勘 12
2.3閱讀後情緒與分析 13
2.3.1情緒分析 13
2.3.2閱讀後情緒 14
3.1研究流程及架構 16
3.2文章來源 18
3.3研究對象 19
3.4實驗平台 22
3.4.1實驗環境 22
3.4.2軟體開發工具 23
3.5實驗設計 29
3.5.1實驗流程 29
3.5.2系統畫面 31
3.5問卷 40
3.6資料分析方法 42
3.6.1資料前處理 42
第四章 研究結果 43
4.1閱聽者回覆 43
4.1.1新聞來源 43
4.1.2新聞內容 44
4.1.3反駁與澄清 46
4.1.4新增題項 46
4.2閱聽者背景對於辨識的影響 48
4.2.1學習領域 48
4.2.2性別 51
4.3性別對於辨識的影響 53
4.4文本特徵分析 56
4.4.1文本情緒詞 56
4.4.2文本標點符號 58
4.5文本特徵對於閱聽者的影響 60
4.5.1閱讀後的情緒 60
4.5.2虛假指數 62
4.5.3XGBoost特徵排序 68
4.6系統功能對閱聽者的影響 74
4.6.1標記功能對於閱聽者的影響 74
4.6.2網路連結數量對於閱聽者的影響 77
4.5.3情緒詞對於閱聽者的影響 79
第五章、結論與建議 81
5.1研究結論 81
5.2研究建議 84
參考文獻 85
附錄 91
附錄1.新聞列表 91
附錄2.CLIWC2015 詞典變項說明 93
附錄3.LIWC 符號轉換對照 96

Aldwairi, M., & Alwahedi, A. (2018). Detecting Fake News in Social Media Networks. Procedia Computer Science, 141, 215-222. https://doi.org/https://doi.org/10.1016/j.procs.2018.10.171
Allcott, H., & Gentzkow, M. (2017). Social Media and Fake News in the 2016 Election. Journal of Economic Perspectives, 31(2), 211-236. https://doi.org/10.1257/jep.31.2.211
Almenar, E., Aran-Ramspott, S., Suau, J., & Masip, P. (2021). Gender Differences in Tackling Fake News: Different Degrees of Concern, but Same Problems [disinformation; fake news; gender; misinformation; perception; Spain]. 2021, 9(1), 10. https://doi.org/10.17645/mac.v9i1.3523
Aloshban, N. (2020). ACT : Automatic Fake News Classification Through Self-Attention Proceedings of the 12th ACM Conference on Web Science, Southampton, United Kingdom. https://doi.org/10.1145/3394231.3397901
Ansari, M. Z., Aziz, M. B., Siddiqui, M. O., Mehra, H., & Singh, K. P. (2020). Analysis of Political Sentiment Orientations on Twitter. Procedia Computer Science, 167, 1821-1828. https://doi.org/https://doi.org/10.1016/j.procs.2020.03.201
Arin, K. P., Mazrekaj, D., & Thum, M. (2023). Ability of detecting and willingness to share fake news. Sci Rep, 13(1), 7298. https://doi.org/10.1038/s41598-023-34402-6
Aïmeur, E., Amri, S., & Brassard, G. (2023). Fake news, disinformation and misinformation in social media: a review. Soc Netw Anal Min, 13(1), 30. https://doi.org/10.1007/s13278-023-01028-5
Balzarotti, S., & Ciceri, M. R. (2014). News Reports of Catastrophes and Viewers' Fear: Threat Appraisal of Positively Versus Negatively Framed Events. Media Psychology, 17(4), 357-377. https://doi.org/10.1080/15213269.2013.826588
Berger, J., & Milkman, K. L. (2012). What makes online content viral? Journal of Marketing Research, 49, 192-205. https://doi.org/10.1509/jmr.10.0353
BROSIUS, H.-B. (1993). The Effects of Emotional Pictures in Television News. Communication Research, 20(1), 105-124. https://doi.org/10.1177/009365093020001005
Chadwick, A., & Vaccari, C. (2019). News sharing on UK social media: Misinformation, disinformation, and correction.
Chang, J.-R., Liang, H.-Y., Chen, L.-S., & Chang, C.-W. (2020). Novel feature selection approaches for improving the performance of sentiment classification. Journal of Ambient Intelligence and Humanized Computing. https://doi.org/10.1007/s12652-020-02468-z
Das, K., Baruah, A., Barbhuiya, F. A., & Dey, K. (2020). Ensemble of ELECTRA for Profiling Fake News Spreaders. Conference and Labs of the Evaluation Forum,
de Hoog, N., & Verboon, P. (2020). Is the news making us unhappy? The influence of daily news exposure on emotional states. Br J Psychol, 111(2), 157-173. https://doi.org/10.1111/bjop.12389
Diaz-Garcia, J. A., Fernandez-Basso, C., Ruiz, M. D., & Martin-Bautista, M. J. (2020). Mining Text Patterns over Fake and Real Tweets. In (pp. 648-660). Springer International Publishing. https://doi.org/10.1007/978-3-030-50143-3_51
Durier, F., Vieira, R., & Garcia, A. C. (2019). Can Machines Learn To Detect Fake News? A Survey Focused on Social Media.
Englmeier, K. (2021). The Role of Text Mining in Mitigating the Threats from Fake News and Misinformation in Times of Corona. Procedia Computer Science, 181, 149-156. https://doi.org/https://doi.org/10.1016/j.procs.2021.01.115
Hassonah, M. A., Al-Sayyed, R., Rodan, A., Al-Zoubi, A. M., Aljarah, I., & Faris, H. (2020). An efficient hybrid filter and evolutionary wrapper approach for sentiment analysis of various topics on Twitter. Knowledge-Based Systems, 192, 105353. https://doi.org/https://doi.org/10.1016/j.knosys.2019.105353
Howard, P. N., Bolsover, G., Kollanyi, B., Bradshaw, S., & Neudert, L.-M. (2017). Junk news and bots during the US election: What were Michigan voters sharing over Twitter. CompProp, OII, Data Memo, 1.
Jain, P. K., Pamula, R., & Ansari, S. (2021). A Supervised Machine Learning Approach for the Credibility Assessment of User-Generated Content. Wireless Personal Communications, 118(4), 2469-2485. https://doi.org/10.1007/s11277-021-08136-5
Johnston, W. M., & Davey, G. C. L. (1997). The psychological impact of negative TV news bulletins: The catastrophizing of personal worries. British Journal of Psychology, 88(1), 85-91. https://doi.org/https://doi.org/10.1111/j.2044-8295.1997.tb02622.x
Kahn, J. H., Tobin, R., xe, e, M., Massey, A. E., & Anderson, J. A. (2007). Measuring Emotional Expression with the Linguistic Inquiry and Word Count. The American Journal of Psychology, 120(2), 263-286. http://www.jstor.org/stable/20445398
Kang, H., Yoo, S. J., & Han, D. (2012). Senti-lexicon and improved Naïve Bayes algorithms for sentiment analysis of restaurant reviews. Expert Systems with Applications, 39(5), 6000-6010. https://doi.org/https://doi.org/10.1016/j.eswa.2011.11.107
Lerner, J. S., Gonzalez, R. M., Small, D. A., & Fischhoff, B. (2003). Effects of Fear and Anger on Perceived Risks of Terrorism: A National Field Experiment. Psychological Science, 14(2), 144-150. http://www.jstor.org/stable/40063785
Lerner, J. S., Li, Y., Valdesolo, P., & Kassam, K. S. (2015). Emotion and Decision Making. Annual Review of Psychology, 66(1), 799-823. https://doi.org/10.1146/annurev-psych-010213-115043
Li, P.-H., Fu, T.-J., & Ma, W.-Y. (2020). Why attention? Analyze BiLSTM deficiency and its remedies in the case of NER. Proceedings of the AAAI Conference on Artificial Intelligence,
Li, Y.-M., & Li, T.-Y. (2013). Deriving market intelligence from microblogs. Decision Support Systems, 55(1), 206-217. https://doi.org/https://doi.org/10.1016/j.dss.2013.01.023
Lin, L. (2023). Digital News Report 2023:Taiwan. Reuters Institute for the Study of Journalism, 2.
Loomba, S., de Figueiredo, A., Piatek, S. J., de Graaf, K., & Larson, H. J. (2021). Measuring the impact of COVID-19 vaccine misinformation on vaccination intent in the UK and USA. Nature Human Behaviour, 5(3), 337-348. https://doi.org/10.1038/s41562-021-01056-1
McIntyre, K. E., & Gibson, R. (2016). Positive News Makes Readers Feel Good: A “Silver-Lining” Approach to Negative News Can Attract Audiences. Southern Communication Journal, 81(5), 304-315. https://doi.org/10.1080/1041794X.2016.1171892
Menczer, F. (2016). The Spread of Misinformation in Social Media Proceedings of the 25th International Conference Companion on World Wide Web, Montréal, Québec, Canada. https://doi.org/10.1145/2872518.2890092
Michalek, J. E., Lisi, M., Awad, D., Hadfield, K., Mareschal, I., & Dajani, R. (2021). The Effects of a Reading-Based Intervention on Emotion Processing in Children Who Have Suffered Early Adversity and War Related Trauma [Original Research]. Frontiers in Psychology, 12. https://doi.org/10.3389/fpsyg.2021.613754
Nakov, P. (2020). Can We Spot the "Fake News" Before It Was Even Written? ArXiv, abs/2008.04374.
Nic Newman. (n.d.). Executive Summary and Key Findings of the 2020 Report. Digitalnewsreport.Org. https://www.digitalnewsreport.org/survey/2020/overview-key-findings-2020
Olney, T. J., Holbrook, M. B., & Batra, R. (1991). Consumer Responses to Advertising: The Effects of Ad Content, Emotions, and Attitude toward the Ad on Viewing Time. Journal of Consumer Research, 17(4), 440-453. https://doi.org/10.1086/208569
Pang, B., & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Found. Trends Inf. Retr., 2(1–2), 1–135. https://doi.org/10.1561/1500000011
Parsigian, E. K. (2013). Mass Media Writing. https://doi.org/10.4324/9780203812143
Paschen, J. (2020). Investigating the emotional appeal of fake news using artificial intelligence and human contributions. Journal of Product & Brand Management, 29(2), 223-233. https://doi.org/10.1108/JPBM-12-2018-2179
Pekrun, R. (2022). Emotions in Reading and Learning from Texts: Progress and Open Problems. Discourse Processes, 59(1-2), 116-125. https://doi.org/10.1080/0163853X.2021.1938878
Pennebaker, J. W., & King, L. A. (1999). Linguistic styles: Language use as an individual difference. Journal of Personality and Social Psychology, 77(6), 1296-1312. https://doi.org/10.1037/0022-3514.77.6.1296
Reddy, H., Raj, N., Gala, M., & Basava, A. (2020). Text-mining-based Fake News Detection Using Ensemble Methods. International Journal of Automation and Computing, 17(2), 210-221. https://doi.org/10.1007/s11633-019-1216-5
Scott, B. (2005). A Contemporary History of Digital Journalism. Television & New Media, 6(1), 89-126. https://doi.org/10.1177/1527476403255824
Simon Kemp (2023). DIGITAL 2023: GLOBAL OVERVIEW REPORT. DATATEPORTAL.https://datareportal.com/reports/digital-2023-global-overview-report.
Shu, K., Bhattacharjee, A., Alatawi, F., Nazer, T. H., Ding, K., Karami, M., & Liu, H. (2020). Combating disinformation in a social media age. WIREs Data Mining and Knowledge Discovery, 10(6), e1385. https://doi.org/https://doi.org/10.1002/widm.1385
Spalenza, M. A., Filho, L. L., França, F. M. G., Lima, P. M. V., & Oliveira, E. d. (2021). LCAD - UFES at FakeDeS 2021: Fake News Detection Using Named Entity Recognition and Part-of-Speech Sequences. IberLEF@SEPLN,
Talaat, A. S. (2023). Sentiment analysis classification system using hybrid BERT models. Journal of Big Data, 10(1), 110. https://doi.org/10.1186/s40537-023-00781-w
Tong, E. M. W. (2010). Personality Influences in Appraisal–Emotion Relationships: The Role of Neuroticism. Journal of Personality, 78(2), 393-417. https://doi.org/https://doi.org/10.1111/j.1467-6494.2010.00620.x
Tripathy, A., Agrawal, A., & Rath, S. K. (2015). Classification of Sentimental Reviews Using Machine Learning Techniques. Procedia Computer Science, 57, 821-829. https://doi.org/https://doi.org/10.1016/j.procs.2015.07.523
Verma, S. (2022). Sentiment analysis of public services for smart society: Literature review and future research directions. Government Information Quarterly, 39(3), 101708. https://doi.org/https://doi.org/10.1016/j.giq.2022.101708
Vosoughi, S., Roy, D., & Aral, S. (2018). The spread of true and false news online. Science, 359(6380), 1146-1151. https://doi.org/doi:10.1126/science.aap9559
Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731-5780. https://doi.org/10.1007/s10462-022-10144-1
Wei-Ching Wang, C.-S. L., Hsu-Cheng Chiang, Kun-Chang Chou. (2021). artificial intelligence, natural language processing, social media, fake news. Chinese Journal of Communication Research, 39, 28.
White, D. M. (1950). The “Gate Keeper”: A Case Study in the Selection of News. Journalism Quarterly, 27(4), 383-390. https://doi.org/10.1177/107769905002700403
Wu, L., Morstatter, F., Carley, K. M., & Liu, H. (2019). Misinformation in Social Media: Definition, Manipulation, and Detection. SIGKDD Explor. Newsl., 21(2), 80–90. https://doi.org/10.1145/3373464.3373475
Yang, C., Lin, K. H. Y., & Chen, H. H. (2007, 2-5 Nov. 2007). Emotion Classification Using Web Blog Corpora. IEEE/WIC/ACM International Conference on Web Intelligence (WI'07),
Yoon, G., Li, C., Ji, Y., North, M., Hong, C., & Liu, J. (2018). Attracting Comments: Digital Engagement Metrics on Facebook and Financial Performance. Journal of Advertising, 47(1), 24-37. https://doi.org/10.1080/00913367.2017.1405753
Zhang, L., Wang, S., & Liu, B. (2018). Deep learning for sentiment analysis: A survey. WIREs Data Mining and Knowledge Discovery, 8(4), e1253. https://doi.org/https://doi.org/10.1002/widm.1253
Django 介紹. (n.d.). Developer.Mozilla.Org. https://developer.mozilla.org/zh-TW/docs/Learn/Server-side/Django/Introduction
Line 數位當責計畫. (2022). 守護優質數位環境 LINE數位當責計畫持續進行！. Line官方部落格. 取自：https://line-tw-official.weblog.to/archives/17062125.html
王若樸(2021).疫情假新聞滿天飛，Line如何用AI加速事實查核？ IThome.取自：https://www.ithome.com.tw/news/145753
何蕙安、陳慧敏. 【Global Fact 10】全球事實查核十年之路.台灣事實查核中心. 取自：https://tfc-taiwan.org.tw/articles/9371
林瑋芳, 黃金蘭, 林以正, 李嘉玲, & Pennebaker, J. W. (2020). 語言探索與字詞計算詞典2015中文版之修訂 [The Revision of the Chinese Linguistic Inquiry and Word Count Dictionary 2015]. 調查研究-方法與應用(45), 73-118.
洪素珍(2016).解析「後真相」的心理──所謂真相，從來就未必真實。獨立評論。取自：https://opinion.cw.com.tw/blog/profile/360/article/5062
陳思樺. (2019). 你知道甚麼是真的嗎？教你分辨假新聞 (Publication Number 2019) 國立臺北大學]. 臺灣博碩士論文知識加值系統.
陳柏青, & 丁學勤. (2018). 應用大數據文字探勘分析網路社群論壇關鍵字－以腕戴式穿戴裝置為例. 運動管理(40), 31-58.
麥金泰爾, & 王惟芬. (2019). 後真相 : 真相已無關緊要,我們要如何分辨真假 (初版 ed.). 時報文化.
國際中心(2020).酒精可以殺死病毒，但絕不能用喝的！伊朗600人自灌酒精送命、3000多人住院[網路新聞]。取自https://www.storm.mg/article/2504914
楊意菁. (2011). 從「網友說」新聞探討公眾角色在新聞報導的變化 [The Discussion of the Changing Role of the Public in News Coverage from the Viewpoint of "Netizen Speaking" News]. 傳播研究與實踐, 1(1), 43-53. https://doi.org/10.6123/jcrp.2011.004
楊意菁. (2013). 網路意見的新聞再現與公眾想像：「網友說」新聞的內容與論述分析 [News Presentation of Internet Opinion and Public Imagination: Content and Discourse Analysis of "Net-User Speaking" News]. 中華傳播學刊(24), 119-164. https://doi.org/10.6195/cjcr.2013.24.04
葉乃靜. (2020). 後真相時代社群媒體上的假新聞分享行為研究 [Sharing Fake News on Social Media in the Era of Post-truth]. 圖書館學與資訊科學, 46(1), 96-112. https://doi.org/10.6245/jlis.202004_46(1).0004
蔡芃敏. (2020). 衛生紙搶購潮誤會大了 經濟部：與口罩原料不一樣. 中央通訊社. https://www.cna.com.tw/news/firstnews/202002070191.aspx