| dc.contributor.advisor | 薛慧敏 | zh_TW |
| dc.contributor.author (Authors) | 黃中廷 | zh_TW |
| dc.contributor.author (Authors) | Huang, Chung-Ting | en_US |
| dc.creator (作者) | 黃中廷 | zh_TW |
| dc.creator (作者) | Huang, Chung-Ting | en_US |
| dc.date (日期) | 2019 | en_US |
| dc.date.accessioned | 4-Mar-2019 19:12:14 (UTC+8) | - |
| dc.date.available | 4-Mar-2019 19:12:14 (UTC+8) | - |
| dc.date.issued (上傳時間) | 4-Mar-2019 19:12:14 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0105354013 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/122378 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 統計學系 | zh_TW |
| dc.description (描述) | 105354013 | zh_TW |
| dc.description.abstract (摘要) | 新聞媒體在資訊傳遞與監督政府上扮演重要的角色，但媒體偏差的問題也伴隨著大量的報導一同產生，尤其是政治新聞。近期Word2vec方法被用來將類別型態的字詞映射至實數向量空間上，經過量化後，字詞間的相關性得以被測量。本論文將Word2Vec應用於台灣電子媒體之新聞資料，透過提取關鍵字的方式加以分析，以探討媒體偏差之存在性。我們並探究Word2Vec中的模型與傳統統計觀點異同之處。本研究使用2014年台灣地區的政治類新聞，比較兩家電子媒體對台北市長候選人相關新聞，另外也檢測word2vec方法中的窗格大小對分析結果的敏感度。我們發現不同的媒體在用字與寫作風格上有明顯差異，另外也存在著政黨偏好的可能性。 | zh_TW |
| dc.description.abstract (摘要) | News media plays an important role in information transmission and supervising the government, but the problem of media bias is accompanied with massive numbers of news especially in political news. Word2Vec is used to map categorical data into real number space. The correlation between words can be measured after quantifying. In this paper, we apply Word2Vec on the news data of Taiwan electronic media, capturing keywords and analyzing them to find out the existence of media bias. We also explore the differences of views between the model in Word2Vec and original statistics concepts. In this research, we use the political news in Taiwan in 2014, comparing news associated with candidates of the mayor in Taipei. On the other hand, we do some detection on the sensitivity of the window size to Word2Vec. Finally we discover that besides different media having different writing habit themselves, they also have the possibility of party preferences. | en_US |
| dc.description.tableofcontents | 第一章 緒論 1第二章 研究方法 4第一節 Word2Vec簡介 4第二節 公式與推導 6第三章 實證分析 9第一節 資料之處理 9第二節 與「柯文哲」高度相關的關鍵字 12第三節 與「連勝文」高度相關的關鍵字 13第四節 窗格的影響 21第四章 結論與建議 24參考文獻 26 | zh_TW |
| dc.format.extent | 1450579 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0105354013 | en_US |
| dc.subject (關鍵詞) | 媒體偏差 | zh_TW |
| dc.subject (關鍵詞) | 政治新聞 | zh_TW |
| dc.subject (關鍵詞) | Word2Vec | zh_TW |
| dc.subject (關鍵詞) | 相關性 | zh_TW |
| dc.subject (關鍵詞) | Media bias | en_US |
| dc.subject (關鍵詞) | Political news | en_US |
| dc.subject (關鍵詞) | Word2Vec | en_US |
| dc.subject (關鍵詞) | Correlation | en_US |
| dc.title (題名) | 基於Word2Vec台灣媒體政治傾向探討 | zh_TW |
| dc.title (題名) | A Study of word2vec: Application of Media Bias Investigation | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | [1] 台北市媒體服務代理商協會,(2017).2017年台灣媒體白皮書.https://maataipei.org/download/2017媒體白皮書/[2] D`Alessio, D, Allen, M,(2000).Media Bias in PresidentialElections: A Meta-Analysis, Journal of Communication,50,133-156.[3] 媒體改造學社、台灣媒體觀察教育基金會、優質新聞發展協會,(2018).【聯合聲明】選舉新聞嚴重失衡，媒體自律形同具文，媒體觀察組織發表嚴厲譴責暨申訴行動聲明.http://www.mediawatch.org.tw/news/9787。[4] Eberl J.-M., Boomgaarden H.G., Wagner M.,(2017).One Bias FitsAll? Three Types of Media Bias and Their Effects on PartyPreferences, Communication Research,44,1125-1148.[5] Sun J.Y., 结巴中文分词.https://github.com/fxsjy/jieba[6] Cavnar W.B., Trenkle J.M.,(1994). N-Gram-Based TextCategorization, Proceedings of SDAIR-94, 3rd Annual Symposium onDocument Analysis and Information Retrieval,161-175.[7] Pennington J., Socher R., Manning C.D.,(2014). GloVe: GlobalVectors for Word Representation, EMNLP 2014,1532-1543.[8] Selivanov D.,(2015). GloVe vs word2vec revisited,http://dsnotes.com/post/glove-enwiki/[9] McCormick C.,(2016). Word2Vec Tutorial-The Skip-Gram Model.http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/[10] Mikolov T., Chen K., corrado G.S., Dean J.,(2013). EfficientEstimation of Word Representations in Vector Space,arXiv:1301.3781v3.[11] Mikolov T., Sutskever I., Chen K., Corrado G.S., Dean J.,(2013).Distributed Representations of Words and Phrases and theirCompositionality, NIPS 2013,3111-3119. | zh_TW |
| dc.identifier.doi (DOI) | 10.6814/THE.NCCU.STAT.003.2019.B03 | en_US |
