English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 113648/144635 (79%)
Visitors : 51672357      Online Users : 367
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
    •  Adv. Search
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/153956


    Title: 深度學「習」：以自然語言處理方法研究 「習近平重要講話」意識形態與時序變化趨勢
    Deep Learning “Xi”: Using Natural Language Processing Important Ideology Model and Timeseries Trends in “Xi Jinping’s Speech”
    Authors: 邵軒磊
    Shao, Hsuan-lei
    Contributors: 問題與研究
    Keywords: 習近平重要講話;自然語言處理;深度學習;計算政治學;文字探勘
    Xi Jinping's Important Speech;Natural Language Processing;Deep Learning;Computational Politics;Text-Mining
    Date: 2024-09
    Issue Date: 2024-10-07 13:15:43 (UTC+8)
    Abstract: 「習近平之發言作為」成為觀察中共政治情勢的核心指標，其個人思想也成為中共政治的重要動力。本研究試圖回答：「習近平意識形態體系特徵與其思想時序變化」，特別是與毛主義的關係。本研究之方法為「計算政治學／計算中國研究」，使用計算機為核心來探索人力難以發現的部分。具體而言，蒐集「習近平系列重要講話資料庫」中之講話文本，作為分析語料。使用程式技術如文字探勘（text mining）、自然語言處理（natural language processing）與深度學習（deep learning）演算法，建立分析模型，進行大量自動標註。本研究具體達成自動化機器處理大量語料，並具體實踐其批次流程分析；其次使用自然語言處理抽取其話語特徵；嘗試模型化其意識形態體系。本研究作為一個原型實驗（prototype experimental）論文，成功實踐了大量資料蒐集與運算，並且將大規模語料做到「概念分類」，並使用深度學習模型來完成標註與分析。具體而言，檢視習近平十年期間（2012年∼2021年）的語詞使用以及其意識形態變化。研究發現，習近平意識形態確實有向毛主義螺旋上升的趨勢，對後毛主義提及較為穩定，但鬥爭傾向自「中美貿易戰」後逐漸升高。
    Xi Jinping’s activities have become the core focus of the CCP’s political landscape, and his ideology has emerged as a significant driving force in Chinese politics. This study aims to answer the question: “What are the characteristics of Xi Jinping’s ideological system and its chronological evolution?” particularly in relation to Maoism. The methodology of this research is rooted in “computational politics/computational Chinese studies,” utilizing computational methods to explore aspects that are difficult to uncover manually. Specifically, the study collects speech texts from the “Xi Jinping Series of Important Speeches Database” as analytical material. By employing programming techniques such as text mining, natural language processing (NLP), and deep learning algorithms, the study builds analytical models for extensive automated annotation.
    This research achieves two primary goals: first, it automates the processing of large volumes of textual data and implements batch process analysis; second, it uses NLP to extract discourse features and attempts to model Xi Jinping’s ideological system. As a prototype experimental paper, it successfully implements large-scale data collection and computation, achieving “concept classification” of extensive corpora and utilizing deep learning models for annotation and new research. Specifically, the study examines the vocabulary usage and ideological changes over Xi Jinping’s ten-year period (2012-2021). The findings indicate that Xi Jinping’s ideology indeed shows a spiral upward trend towards Maoism, with a relatively stable reference to post-Maoism, but with an increasing tendency towards struggle following the “China-U.S. trade war.”
    Relation: 問題與研究, 63(3), 79-108
    Data Type: article
    DOI 連結: https://doi.org/10.30390/ISC.202409_63(3).0003
    DOI: 10.30390/ISC.202409_63(3).0003
    Appears in Collections:[問題與研究 TSSCI] 期刊論文

    Files in This Item:

    File Description SizeFormat
    63-3-3.pdf6479KbAdobe PDF58View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    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 ©   - Feedback