淡江大學機構典藏:Item 987654321/87732
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 62830/95882 (66%)
造访人次 : 4033276      在线人数 : 998
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/87732


    题名: 部落格文章情感分析之研究
    其它题名: A study of sentimental analysis in blog articles
    作者: 簡之文;Chien, Chih-Wen
    贡献者: 淡江大學資訊管理學系碩士班
    蕭瑞祥
    关键词: 情感分析;支援向量機;知網;主觀情緒;sentimental analysis;SVM;Hownet;subjective emotion
    日期: 2012
    上传时间: 2013-04-13 11:36:49 (UTC+8)
    摘要: 如何在龐大的網路社群文章中,有效且快速的擷取所要的情感評論,是情感分析(Sentiment Analysis)重要的基礎工作,本研究選擇在語句層級探討,分析文章中的主觀情緒評論語句。嘗試找出主觀情緒語句與非主觀情緒語句的判斷模式。本研究採用系統發展研究法,使用SVM(Support Vector Machine)工具將主觀情緒語句進行訓練與測試,實驗中再將SVM產出的分類與實際分類做比對,計算其準確率做為系統驗證的依據。
    根據本研究的實驗發現,依據SVM工具產出的分類,若將屬性詞與意見片語之距離容許誤差值設為3,可大幅提升距離分類準確率,且可減少距離比對的運算成本,而屬性詞類的分類特徵較能區分主觀情緒語句與意見片語距離的關係,與相關研究中的演算法比較後,可將過濾非主觀情緒階段的準確率提升13%,達到66%。期望本研究能為部落格,甚至其他社群網路情感分析之研究與實務有所貢獻。
    How to capture the emotional opinion efficiently and quickly in a lot of network community articles is an important basic work for Sentiment Analysis. This study is discussed in the sentence-level analysis of the subjective emotional comment sentences in the article, and tries to find out a judgment model of subjective emotional sentences and non-subjective emotional sentences. This study adopts Systems Development Methodology, and it uses SVM tool to train and test the subjective emotional sentences. In this experiment, it compares the classification of SVM with the actual classification and it calculates the accuracy as the basis for system verification.
    On the basis of the classification of SVM, this study found if the tolerance value of the distance between attribute word and opinion phrase is set to 3, it will significantly improve the accuracy of distance classification and reduce the computing cost of distance comparison, and then the classification feature of the attribute words is better than negative words and opinion words in recognizing the distance relationship between attribute word and opinion phrase.
    显示于类别:[資訊管理學系暨研究所] 學位論文

    文件中的档案:

    档案 大小格式浏览次数
    index.html0KbHTML270检视/开启

    在機構典藏中所有的数据项都受到原著作权保护.

    TAIR相关文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈