English  |  正體中文  |  简体中文  |  Items with full text/Total items : 52068/87197 (60%)
Visitors : 8906022      Online Users : 312
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/94401

    Title: 中文意見探勘系統之新增意見詞演算法
    Other Titles: Algorithm for pick out new opinion word of Chinese opinion mining system
    Authors: 王天煜;Wang, Tien-Yu
    Contributors: 淡江大學資訊工程學系碩士在職專班
    Keywords: 意見探勘;中文;意見詞;Opinion Mining;Chinese;Opinion Word
    Date: 2013
    Issue Date: 2014-01-23 14:34:44 (UTC+8)
    Abstract: 因為建立或維護詞庫型意見探勘系統,需耗費大量人力或時間,本研究試圖將這些耗費大量人力的工作簡化,原來建立或維護詞庫時需要看很多文章,並挑出針對領域有用的意見詞之後新增至詞庫,現在只要執行演算法將文章內新的意見詞挑出,之後判斷演算法所挑出的新意見詞及比照新意見詞和句子是否為對領域有用的意見詞並新增至詞庫。由於檢查演算法挑出的新意見詞比直接看文章來得省時省力,進而達到降低詞庫建置或維護的成本。
    Due to huge manpower and time consuming for establishing and maintaining a word library type Opinion Mining system, the study attempts to simplify the operation of huge manpower and time consuming, thus the original reading many articles for establishing and maintaining the word library, where Opinion Word useful to the domain have to be pickup and added to the word library, with the process of the study, it only needs to execute algorithms to pickup new Opinion Word in articles, then determine whether the pickup Opinion Word is useful to the domain by comparing the pickup Opinion Word and sentence, and then add to word library. Owing to checking new Opinion Word picked out by algorithms is much time and manpower saving comparing to reading articles directly, moreover word library establishing and maintaining cost can be reduced.
    Appears in Collections:[資訊工程學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat

    All items in 機構典藏 are protected by copyright, with all rights reserved.

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