政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/135888
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 113648/144635 (79%)
造访人次 : 51605320      在线人数 : 786
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻
    政大機構典藏 > 商學院 > 統計學系 > 期刊論文 >  Item 140.119/135888


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/135888


    题名: 以文字探勘技術分析臺灣四大報文字風格
    A Study of Text Mining on Taiwan`s Newspapers
    作者: 余清祥
    Yue, Jack C.
    葉昱廷
    Ye, Yu-Ting
    贡献者: 統計系
    关键词: 寫作風格; 臺灣四大報; 探索性資料分析; 相似指標; 關鍵詞
    writing style; Taiwan`s newspaper; exploratory data analysis; similarity index; keywords
    日期: 2020-10
    上传时间: 2021-06-25 10:17:05 (UTC+8)
    摘要: 媒體對同一主題的報導經常有明顯差異，本文以報紙報導風格為研究目標，比較臺灣四大報《蘋果日報》、《自由時報》、《聯合報》、《中國時報》的報導風格。避免報紙立場及題材造成的干擾，本文選取每天頭版頭條新聞，資料期間為2012年至2018年，其中頭條標題涵蓋四大報，但頭條內文僅有《蘋果日報》、《自由時報》。本文分析常用詞彙、句長、標點、虛字，發現四大報頭條標題及內文的用字風格不完全相同，其中標題的Jaccard指標將同時期報導放在同一群，Yue指標將四大報分成三群；內文分析發現《自由時報》傾向政治新聞，《蘋果日報》傾向社會新聞，以能夠代表兩報的常見詞彙為解釋變數，統計及機器學習模型都能準確地區隔《自由時報》或《蘋果日報》。
    Like an author`s writing style, every newspaper has its own opinion and narrative methods. In this study, our goal is to explore the reporting styles of Taiwan`s four major newspapers (Apple Daily, Liberty Times, United Daily News, and China Times) and to compare their differences. We chose the headline news for analysis to prevent the influence of nuisance factors, such as differences in political positions and target audience. The newspaper headlines considered are between 2012 and 2018. The titles of headlines are considered for all four newspapers but the content of headlines is available only for Apple Daily and Liberty Times. We first applied the methods of exploratory data analysis (EDA), such as Jaccard index and Yue index, for the word frequencies and word types to evaluate the similarities between four newspapers. In addition, we also compare the length of sentences, punctuation, and function words of four newspapers. Finally, we used statistical and machine learning methods to distinguish if the news articles are from Apple Daily or Liberty Times. The analysis results showed that there are significant differences between four newspapers. For the headline titles, the Jaccard index grouped titles by time and the Yue index grouped titles by the media (i.e., three groups). For the headline contents, we found that the articles of Liberty Times emphasize political terms and those of Apple Daily focus on social affairs and crime problems. All classification methods have high accuracy if we chose frequently used two-word phrases as the independent variables.
    關聯: 數位典藏與數位人文, Vol.6, pp.67-94
    数据类型: article
    DOI 連結: https://doi.org/10.6853/DADH.202010_(6).0003
    DOI: 10.6853/DADH.202010_(6).0003
    显示于类别:[統計學系] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    171.pdf1764KbAdobe PDF2280检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈