資料載入中.....
|
請使用永久網址來引用或連結此文件:
https://nccur.lib.nccu.edu.tw/handle/140.119/158687
|
| 題名: | 台灣政論節目之大型語言模型檢索增強監測系統設計
Designing a Retrieval-Augmented Monitoring System for Political Talk Shows in Taiwan Using Large Language Models |
| 作者: | 施楷
See, Kai |
| 貢獻者: | 卞中佩
Pien, Chung-pei
施楷
See, Kai |
| 關鍵詞: | 大型語言模型
檢索增強
嵌入模型
事實查核
自動語音辨識
政論節目
逐字稿
片段切割
裴洛西訪台
Large language model
Retrieval augmented
Embedding models
Fact-checking
Automated speech recognition
Political talk shows
Transcripts
Chunking
Pelosi visit to Taiwan |
| 日期: | 2025 |
| 上傳時間: | 2025-08-04 15:03:19 (UTC+8) |
| 摘要: | 這個專業實務報告探討大型語言模型（LLMs）與基於向量的檢索系統在台灣政論節目語境中的應用。透過從自建的節目逐字稿資料庫檢索某議題「何時」、「由誰」和「在哪個節目」被討論，研究希望能夠輔助在台的事實查核組織的工作流程，協助查核記者更有效地篩選與調查所需跟進的議題。研究使用2022年7月20日與8月1日的逐字稿資料，聚焦於時任美國眾議院議長裴洛西訪台前的輿論動態，建立一個整合自動語音辨識、片段切割、利用 OpenAI 的 text-embedding-3-large 與 text-embedding-ada-002 模型進行嵌入、向量搜尋與查詢策略的處理流程。研究比較了零樣本（zero-shot）檢索、關鍵字擴增查詢以及LLM重新排序的方法，以評估在各種主題上的逐字稿片段檢索表現。研究採用精確率（precision）、召回率（recall）與 F1 分數作為評估指標，分析不同大小主題在兩個日期下的表現與權衡。結果顯示，雖然在檢索查詢中納入足夠的背景資料或關鍵字時，基於 LLM 的檢索方法可展現出中等強度的召回表現，但政論節目逐字稿內容龐雜、雜訊多且結構鬆散，限制了其精確率。此研究同時突顯了此類系統用在台灣的媒體環境中的潛力與限制。
This capstone project looks at the application of large language models (LLMs) and a vector-based retrieval system in context of Taiwan’s political talk shows. It aims to supplement the existing fact-checking workflows utilized by fact-checkers in Taiwan by identifying when, whom and where an issue is discussed, which helps in both the topic selection and investigation stages of the fact-checking process. Using transcripts from 20 July 2022 and 1 August 2022 leading up to former United States House of Representatives Speaker Nancy Pelosi’s visit to Taiwan, the study builds a pipeline that integrates automated speech recognition, chunk segmentation, embedding using OpenAI’s text-embedding-3-large and text-embedding-ada-002 models, vector search and query strategies. The project compares the zero-shot retrieval, keyword-augmented query and LLM-reranking approach to assess the performance of the different approaches to retrieve transcript segments for a range of topics. Precision, recall and F1 score metrics were used to evaluate the performance across large, medium and small topics across the 2 dates, providing insights into the performance and trade-offs. Findings show that while the LLM-based retrieval method can provide a moderately-strong recall performance when sufficient context is incorporated in the retrieval query, the noisy, voluminous and unstructured nature of political talk show transcripts tend to limit the precision performance. The project also highlights the potential and limitation of such a system in context of Taiwan’s media environment. |
| 參考文獻: | English References
AIT. (2022, August 3). Speaker of the House Pelosi Leads Senior Congressional Delegation to Taiwan. https://www.ait.org.tw/speaker-of-the-house-pelosi-leads-senior-congressional-delegation-to-taiwan-departure/
Anthropic. (2024). The Claude 3 Model Family: Opus, Sonnet, Haiku. https://assets.anthropic.com/m/61e7d27f8c8f5919/original/Claude-3-Model-Card.pdf
BBC News. (2022, July 31). Nancy Pelosi begins Asia tour, with no mention of Taiwan. https://www.bbc.com/news/world-us-canada-62367362
Benack, E. (2022, July 28). Han Kuang Exercise: Navy and Air Force simulate joint attack. https://en.rti.org.tw/news/view/id/2007951
Bhavsar, P. (2024, March 5). Mastering RAG: How to select an embedding model. https://galileo.ai/blog/mastering-rag-how-to-select-an-embedding-model
Breuer, A., Dietrich, B. J., Crespin, M. H., Butler, M., Pyrse, J. A., & Imai, K. (2025). Using AI to Summarize US Presidential Campaign TV Advertisement Videos, 1952–2012. https://doi.org/10.48550/arXiv.2503.22589
Burtsev, M., Reeves, M., & Job, A. (2024). The Working Limitations of Large Language Models. MIT Sloan Management Review. https://lims.ac.uk/documents/undefined-1.pdf
Chan, C., Xu, C., Yuan, R., Luo, H., Xue, W., Guo, Y., & Fu, J. (2024). RQ-RAG: Learning to refine queries for Retrieval Augmented Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.00610
Chen, Y., Lin, L., & Liu, T. (2022, July 25). Lin explains thesis events, denies plagiarism. Taipei Times. https://www.taipeitimes.com/News/taiwan/archives/2022/07/25/2003782381
Cheng, M., Tsai, C., & Chin, J. (2022, July 6). Accusations of plagiarism by mayor spark a fracas. Taipei Times. https://www.taipeitimes.com/News/taiwan/archives/2022/07/06/2003781239
Cohen, D. (2022, July 31). Pelosi confirms trip to Asia but doesn’t mention Taiwan. Politico. https://www.politico.com/news/2022/07/31/pelosi-asia-trip-taiwan-00048822
Deas, N., & McKeown, K. (2024). Summarization of Opinionated Political Documents with Varied Perspectives. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.04093
DeepSeek-AI. (2025). DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. https://arxiv.org/html/2501.12948v1
Dhanakotti, K. (2024, August 15). RAGAS for RAG in LLMS: A Comprehensive Guide to Evaluation Metrics. Medium. https://dkaarthick.medium.com/ragas-for-rag-in-llms-a-comprehensive-guide-to-evaluation-metrics-3aca142d6e38
Dotson, J. (2022, August 10). The highlights of Taiwan’s 2022 Han Kuang military exercise. Global Taiwan Institute. https://globaltaiwan.org/2022/08/the-highlights-of-taiwans-2022-han-kuang-military-exercise/
Duarte, A., V., Marques, J., Graça, M., Freire, M., Li, L., & Oliveira, A. L. (2024). LumberChunker: Long-Form Narrative Document Segmentation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2406.17526
Epstein, J. (2022, August 3). China announces it will be conducting military drills, including live-fire exercises, all around Taiwan as Pelosi arrives for historic visit. Business Insider. https://www.businessinsider.com/china-military-exercises-around-taiwan-nancy-pelosi-visit-2022-8
Es, S., James, J., Espinosa-Anke, L., & Schockaert, S. (2023). RAGAS: Automated Evaluation of Retrieval Augmented Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2309.15217
Gao, L., Ma, X., Lin, J., & Callan, J. (2022). Precise Zero-Shot Dense Retrieval without Relevance Labels. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2212.10496
Google Trends. (n.d.). Trends. https://trends.google.com/trends/
Gurdeniz, E., Blumenfeld, I. G., & Wilson, J. T. (2024, October 11). How companies can use LLM-Powered Search to create value. Harvard Business Review. https://hbr.org/2024/10/how-companies-can-use-llm-powered-search-to-create-value
Haenle, P., & Sher, N. (2022, August 17). How Pelosi’s Taiwan visit has set a new status quo for U.S-China tensions. Carnegie Endowment for International Peace. https://carnegieendowment.org/posts/2022/08/how-pelosis-taiwan-visit-has-set-a-new-status-quo-for-us-china-tensions?lang=en
Holland, S. (2022, July 13). Biden en route to Israel for high-stakes Middle East visit. Reuters. https://www.reuters.com/world/middle-east/biden-en-route-israel-high-stakes-middle-east-visit-2022-07-13/
Jagerman, R., Zhuang, H., Qin, Z., Wang, X., & Bendersky, M. (2023). Query expansion by prompting large language models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2305.03653
Joshi, A. (2024, June 18). How to choose the right chunking strategy for your LLM application | MongoDB. https://www.mongodb.com/developer/products/atlas/choosing-chunking-strategy-rag/
Kuhn, K., Kersken, V., Reuter, B., Egger, N., & Zimmermann, G. (2024). Measuring the accuracy of automatic speech recognition solutions. ACM Transactions on Accessible Computing, 16(4), 1–23. https://doi.org/10.1145/3636513
Kumar, V. (2024, August 28). Chunking Strategies for RAG in Generative AI. ADaSci. https://adasci.org/chunking-strategies-for-rag-in-generative-ai/
Kyodo News. (2022, August 5). Kishida, Pelosi agree to work for peace, stability in Taiwan Strait. Kyodo News+. https://english.kyodonews.net/news/2022/08/fe2d101d1e0a-japan-pm-meets-with-us-house-speaker-pelosi-after-taiwan-visit.html
Lee, W. (2011). Mediated politics in Taiwan political talk shows and democracy. Taiwan Journal of Democracy, 7(2), 49–67. https://doi.org/10.29654/tjd.201112.0004
Li, D., Chen, T., Zadikian, A., Tung, A., & Chilton, L. B. (2023, April 19). Improving Automatic Summarization for Browsing Longform Spoken Dialog. https://doi.org/10.1145/3544548.3581339
Li, J., Yuan, Y., & Zhang, Z. (2024). Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2403.10446
Li, S., Stenzel, L., Eickhoff, C., & Bahrainian, S. A. (2025). Enhancing Retrieval-Augmented Generation: A Study of Best Practices. https://doi.org/10.48550/arXiv.2501.07391
Li, Z., Wang, J., Jiang, Z., Mao, H., Chen, Z., Du, J., Zhang, Y., Zhang, F., Zhang, D., & Liu, Y. (2024). DMQR-RAG: Diverse Multi-Query Rewriting for RAG. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2411.13154
Lin, L. (2024, June 17). Taiwan. Reuters Institute for the Study of Journalism. https://reutersinstitute.politics.ox.ac.uk/digital-news-report/2024/taiwan
Lyu, K., Lyu, R., & Chang, H. (2024). Real-time multilingual speech recognition and speaker diarization system based on Whisper segmentation. PeerJ Computer Science, 10, e1973. https://doi.org/10.7717/peerj-cs.1973
Mastering LLM. (2024, November 2). 11 Chunking Strategies for RAG — Simplified & visualized. Medium. https://masteringllm.medium.com/11-chunking-strategies-for-rag-simplified-visualized-df0dbec8e373
Matarazzo, A., & Torlone, R. (2025). A Survey on Large Language Models with some Insights on their Capabilities and Limitations. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2501.04040
Mercer, P. (2022, August 5). Australia urges restraint as regional tensions rise over Pelosi Taiwan visit. Voice of America. https://www.voanews.com/a/australia-urges-restraint-as-regional-tensions-rise-over-pelosi-taiwan-visit-/6688052.html
Myscale. (2024, June 26). The Ultimate Guide to Evaluate RAG System components: What you need to know. https://myscale.com/blog/ultimate-guide-to-evaluate-rag-system/
Nguyen, T. M. A. (2022, August 5). Pelosi’s visit to Taiwan creates a headache for ASEAN countries. The Diplomat. https://thediplomat.com/2022/08/pelosis-visit-to-taiwan-creates-a-headache-for-asean-countries/
OpenAI. (2023). GPT-4 Technical Report. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2303.08774
OpenAI. (2024, January 25). New embedding models and API updates. https://openai.com/index/new-embedding-models-and-api-updates/
Pazur, B. (2025, February 1). What is DeepSeek? Everything to know about the new Chinese AI tool. Yahoo Tech. https://tech.yahoo.com/ai/articles/deepseek-everything-know-chinese-ai-130018659.html
Peterson Health Technology Institute. (2025). Adoption of Artificial Intelligence in Healthcare Delivery Systems: Early Applications and Impacts. https://phti.org/wp-content/uploads/sites/3/2025/03/PHTI-Adoption-of-AI-in-Healthcare-Delivery-Systems-Early-Applications-Impacts.pdf
Qwen Team. (2025, April 29). QWeN3: Think deeper, act faster. Qwen. https://qwenlm.github.io/blog/qwen3/
Rawnsley, M., Smyth, J., & Sullivan, J. (2016). Taiwanese Media Reform. Journal of the British Association for Chinese Studies, 6. https://bacsuk.org.uk/wp-content/uploads/2017/01/JBACS-6Rawnsley.pdf
Ray, P. P. (2023). ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet of Things and Cyber-Physical Systems, 3, 121–154. https://doi.org/10.1016/j.iotcps.2023.04.003
Ray, S. (2022, August 3). Pelosi says U.S. is determined to ‘Preserve democracy’ as she meets Taiwanese president. Forbes. https://www.forbes.com/sites/siladityaray/2022/08/03/pelosi-says-us-is-determined-to-preserve-democracy-as-she-meets-taiwanese-president/
Sai, M. (2025, March 8). Open-Source large language models and their maximum input token capacities: A Comprehensive analysis. Medium. https://medium.com/@saimoguloju2/open-source-large-language-models-and-their-maximum-input-token-capacities-a-comprehensive-7d663347ec61
Sevastopulo, D., & Hille, K. (2022, July 19). Nancy Pelosi to visit Taiwan next month amid China tensions. Financial Times. https://www.ft.com/content/09669099-1565-4723-86c9-84e0ca465825
Smith, B., & Troynikov, A. (2024). Evaluating chunking strategies for retrieval. In Chroma Research. https://research.trychroma.com/evaluating-chunking
Taiwan Factcheck Center. (n.d.). Our Fact-Checking Process. Taiwan Factcheck Center https://en.tfc-taiwan.org.tw/en_tfc_299/#
Tong, L., Ge, Q., & 盖振华. (2024). Achieving higher factual accuracy in Llama LLM with weighted distribution of Retrieval-Augmented Generation. https://doi.org/10.31219/osf.io/ctw8v
Wang, R., Xu, Z., & Lin, F. X. (2024). Efficient whisper on streaming speech. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2412.11272
Wijaya, C. Y. (2025, March 11). 9 Chunking strategies to improve RAG performance. Non-Brand Data. https://www.nb-data.com/p/9-chunking-strategis-to-improve-rag
Wodicka, B. (2024, December 31). Content chunking: a foundation of effective AI in knowledge work - Applied Information Sciences. Applied Information Sciences. https://www.ais.com/content-chunking-a-foundation-of-effective-ai-in-knowledge-work/
Wyndham, A. (2022, October 3). How big of a deal is ‘Whisper’ for ASR and multilingual transcription? Slator. https://slator.com/how-big-a-deal-is-whisper-for-asr-multilingual-transcription/
Xu, B., Chen, Y., Wen, Z., Liu, W., & He, B. (2025). Evaluating small language models for news Summarization: Implications and factors influencing performance. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2502.00641
Xu, Y., Hu, L., Zhao, J., Qiu, Z., Ye, Y., & Gu, H. (2024). A survey on multilingual large language models: corpora, alignment, and bias. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2404.00929
Yang, E., Amar, J., Lee, J. H., Kumar, B., & Jia, Y. (2024). The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2407.18044
Yenduri, G., Ramalingam, M., Selvi, G. C., Supriya, Y., Srivastava, G., Maddikunta, P. K. R., Raj, G. D., Jhaveri, R. H., Prabadevi, B., Wang, W., Vasilakos, A. V., & Gadekallu, T. R. (2024). GPT (Generative Pre-Trained Transformer)— a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions. IEEE Access, 12, 54608–54649. https://doi.org/10.1109/access.2024.3389497
Zhao, J., Ji, Z., Qi, P., Niu, S., Tang, B., Xiong, F., & Li, Z. (2024). Meta-Chunking: Learning efficient text segmentation via logical perception. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.12788
中文參考文獻
柯詠薰. (2022). 電視時事性談話節目製播關鍵因素指標建構 [國立政治大學]. https://ah.lib.nccu.edu.tw/item?item_id=162053&locale=en
李子民. (2019). 從要求到給予:台灣政論節目中「好不好」與「好嗎」的知識轉換 [國立臺灣大學]. https://hdl.handle.net/11296/ynmggw
劉彥含. (2014). 臺灣政論節目內容框架分析-以油電雙漲議題為例 [銘傳大學]. https://hdl.handle.net/11296/55w6p7
唐士哲. (2014). 從政治化媒介到媒介化政治：電視政論節目作為制度化的政治實踐. 中華傳播學刊, 25, 3–41. https://www.airitilibrary.com/Publication/Index/17263581-201406-201407010002-201407010002-3-41
馮昭. (2013). 臺灣政論談話性節目之政經分析,1993-2013. [國立臺灣大學]. https://doi.org/10.6342/ntu.2013.01925
郭為鵬. (2012). 政論性談話節目閱聽眾收視行為與評價 [銘傳大學]. https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dnclcdr&s=id=%22100MCU05375022%22.&searchmode=basic
游惠鈞. (2010). 臺灣政論節目中的政治意識型態之社會語用學研究 [國立政治大學]. https://hdl.handle.net/11296/6y7n7q
邱一峰. (2008). 台灣觀眾收視評價與收視率關聯性之分析:以政論談話性節目為例 [國立中山大學]. https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22096NSYS5227016%22.&searchmode=basic
萬巧蓉. (2025, January 7). 假訊息認知調查:95%民眾曾收過假訊息 7成受訪者認事實查核機構角色日益重要. 卓越新聞獎基金會. https://feja.org.tw/77922/
台灣議題研究中心. (2024, September 19). 政論名嘴誰是聲量王?數據揭「這人」聲量領先群雄人氣超旺. https://www.tpoc.com.tw/ArticlePage/3689eca5-29a8-4f30-882c-a7c1bd1c3f23
張卿卿, & 卓牧融. (2024, September 24). 中央研究「大家在討論些什麼?」-2023年政論節目主題探討. 中央研究院人社中心調查研究專題中心 Center for Survey Research. https://survey.sinica.edu.tw/?p=19068&lang=zh
劉美恩. (2024, November 27). TWNIC公布2024年《台灣網路報告》應對不實資訊與AI內容挑戰 | 熱門亮點 | 商情 | 經濟日報. 經濟日報. https://money.udn.com/money/story/5635/8389494
國家通訊傳播委員會. (2024). 112 年 NCC 傳播監理報告. In 電臺與內容事務處. 國家通訊傳播委員會. https://www.ncc.gov.tw/chinese/files/24061/2606_50347_240613_1.pdf
許良亦, & 王希. (2023, December 12). 旺中、三立觀眾世界觀兩極,YouTube 新聞及政論節目環境極化,妨礙民主社會互信. 台灣資訊環境研究中心 IORG. https://iorg.tw/_en/a/youtube-news-polarization#h2-7
財團法人台灣網路資訊中心. (2024). 台灣網路報告2024. 財團法人台灣網路資訊中心. https://report.twnic.tw/2024/assets/download/TWNIC_TaiwanInternetReport_2024_CH_summary.pdf
中央通訊社. (2022, August 1). 華爾街日報:裴洛西本週訪台 將會見台灣官員. 中央社 CNA. https://www.cna.com.tw/news/aipl/202208010371.aspx
王其. (2019, August 5). 政論節目大爆炸的秘密計算. 聚傳媒. https://j-media.tw/Article/Detail/9624
陳清河. (2018, May 8). 【Yahoo論壇/陳清河】廉價的電視政論節目 您真的愛看嗎? Yahoo News. https://tw.news.yahoo.com/%E3%80%90yahoo%E8%AB%96%E5%A3%87%EF%BC%8F%E9%99%B3%E6%B8%85%E6%B2%B3%E3%80%91%E5%BB%89%E5%83%B9%E7%9A%84%E9%9B%BB%E8%A6%96%E6%94%BF%E8%AB%96%E7%AF%80%E7%9B%AE-%E6%82%A8%E7%9C%9F%E7%9A%84%E6%84%9B-005708175.html
台灣事實查核中心. (2023, February 24). 【錯誤】網傳「美國俄亥俄州議員到台灣向民進黨蔡英文政府推銷農產品,台灣人民可能吃到嚴重戴奧辛污染的農產品」? 台灣事實查核中心. https://tfc-taiwan.org.tw/fact-check-reports/migration-8845/
台灣事實查核中心. (2022, August 19). 事實查核機構忙什麼?解密事實查核工作的流程與甘苦。民間的事實查核組織如何選題、如何查證?專訪葉子揚(MyGoPen 創辦人/總編審)、陳慧敏(台灣事實查核中心 總編審) [Video]. YouTube. https://www.youtube.com/watch?v=xHxGLXeRd5E
巫鴻瑋, & 黃羿馨. (2025, January 8). 新竹棒球場案調查進度到哪? 新竹地檢署:持續偵辦中. 聯合新聞網. https://udn.com/news/story/7315/8476125
洪詩宸, & 鄭婷方. (2023, December 28). 假訊息擾台/看完會憤怒「就是這樣!沒錯!」 認識假訊息的操縱機制. 公視新聞網 PNN. https://news.pts.org.tw/article/673654%E2%89%88
朱曼寧. (2021, June 30). 中天走過關台衝擊 YouTube訂閱破257萬. NOWnews今日新聞. https://www.nownews.com/news/5312127?srsltid=AfmBOopR1oRLIqbSGPR2_7t10CWeUH_-S1PrugQZ-VS2aamnIg7-jJf5
林恕暉. (2017, January 27). 張金策與1990年代的台灣左翼媒體: 《群眾》雜誌及《群眾之聲》電台(四) | 公民行動影音紀錄資料庫. 公民行動影音紀錄資料庫. https://www.civilmedia.tw/archives/59943
網路溫度計. (2022a, August 17). 台北市長激戰!民調:「三腳督」支持度差距不到4%. TVBS. https://news.tvbs.com.tw/politics/1879543
網路溫度計. (2022b, October 8). 針砭時事怎能少了他們 十大政論節目主持人. 針砭時事怎能少了他們 十大政論節目主持人｜每日調查. https://dailyview.tw/daily/3488
范榮達, & 程嘉文. (2024, July 1). 軍方要求宮廟屯彈藥 後指部:演練 非實質放置. 聯合新聞網. https://udn.com/news/story/10930/8064852
臺北市政府秘書處. (2022, July 19). 舉辦雙城論壇 臺北市與上海市簽署三項合作備忘錄. 臺北市政府秘書處. https://sec.gov.taipei/News_Content.aspx?n=49B4C3242CB7658C&sms=72544237BBE4C5F6&s=BCF03A9808EE3604
蘇思雲. (2022, July 20). 統一集團收購台灣家樂福 中華信評:進一步支撐獲利. 中央社 CNA. https://www.cna.com.tw/news/afe/202207200332.aspx
邱晟軒. (2022, August 20). 「以民為先,拖去旁邊」陳時中臉書被灌爆 網:你把萬華人抬走了. ETtoday新聞雲. https://www.ettoday.net/news/20220720/2298713.htm
郭佳欣, 吳昕晨, & 黃心俞. (2020, April 9). 政論節目存真偽 唯閱聽眾能改變現況. 世新大學小世界. http://shuj.shu.edu.tw/blog/2020/04/09/%E6%94%BF%E8%AB%96%E7%AF%80%E7%9B%AE%E5%AD%98%E7%9C%9F%E5%81%BD-%E5%94%AF%E9%96%B1%E8%81%BD%E7%9C%BE%E8%83%BD%E6%94%B9%E8%AE%8A%E7%8F%BE%E6%B3%81/
陳培煌. (2024, July 31). 一紙公文牽動宮廟放彈藥風向 專家:僅憑彈藥儲存難認違反國際法. 台灣事實查核中心. https://tfc-taiwan.org.tw/migration_article_105455_10858/
陳祖傑. (2022, July 28). 【專題】新竹棒球場重生為何惹議? 公視新聞網 PNN. https://news.pts.org.tw/curation/92
陳姝君, & 莊志成. (2018, April 19). 揭穿假新聞、假訊息 將成立「事實查核中心」. 公視新聞網. https://news.pts.org.tw/article/391719
Ihower. (2024, August 11). 使用繁體中文評測 RAG 的 Chunking 切塊策略. Ihower { Blogging }. https://ihower.tw/blog/archives/12373
Shengti. (2023, December 15). YouTube直播新聞台頻道整理:台灣各大新聞直播與全球各國新聞頻道線上免費看 - 電腦王阿達. 電腦王阿達. https://www.koc.com.tw/archives/524892
MyGoPen. (n.d.). 查證準則｜如何進行查證. MyGoPen. https://www.mygopen.com/p/blog-page_25.html |
| 描述: | 碩士
國立政治大學
全球傳播與創新科技碩士學位學程
111zm1045 |
| 資料來源: | http://thesis.lib.nccu.edu.tw/record/#G0111ZM1045 |
| 資料類型: | thesis |
| 顯示於類別: | [全球傳播與創新科技碩士學位學程] 學位論文
|
文件中的檔案:
| 檔案 |
描述 |
大小 | 格式 | 瀏覽次數 |
|---|
| 104501.pdf | | 2271Kb | Adobe PDF | 0 | 檢視/開啟 |
|
在政大典藏中所有的資料項目都受到原著作權保護.
|
