English  |  正體中文  |  简体中文  |  Items with full text/Total items : 51511/86795 (59%)
Visitors : 8279262      Online Users : 101
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/987654321/105549


    Title: 未來性資訊檢索系統基於網路論壇之研究
    Other Titles: Future related information retrieval system base on online forum
    Authors: 林祐任;Lin, You-Ren
    Contributors: 淡江大學資訊管理學系碩士班
    蕭瑞祥;Shaw, Ruey-Shiang
    Keywords: 意見探勘;意見單元;未來性資訊;情感分析;Opinion Mining;Opinion unit;Future Related wordings;sentimental analysis
    Date: 2015
    Issue Date: 2016-01-22 14:58:53 (UTC+8)
    Abstract: 時至今日,利用社群網路平台發表自我感受及想法成為趨勢,使得產品評論資訊更容易的被發表及傳播。本研究結合『未來學』、『意見探勘』、『情感分析』三個領域。本研究採用 Nunamaker (1991)等人所提出之系統發展研究法,旨在分析網路評論,整理出網友對於產品的期望,讓開發商更直接簡便的了解消費者的當下需求與未來趨勢。本研究的實驗對象為華碩公司所推出的手機「Padfone變形手機」、「Zenfone智慧型手機」兩種系列產品的評價,實驗資料集來自Mobile01小惡魔論壇的文章資料。文章日期蒐集範圍分別以該系列首次發表年度開始。整體準確率達89%。而未來詞與意見單元之修飾距離為8以內時,未來性意見準確率達60%。最後以圖表呈現產品的意見狀況,表達使用者對產品各部件的意見與期許。
    Texting products usage experience and comments in social media community has been a tendency of most people new behavior. This research is to develop the model of combined with “future related wordings”, “opinion unit retrieval”, and “sentimental analysis” methods for exploring and analyzing text-oriented people opinions and comments. This system prototype adopting with Nunamaker(1991) system development method is to demonstrate the amount of positive and negative in time-frame curve of product opinions as well as to search the possible future related wordings for estimating the needs of product future design.
    This study is based on ASUS mobile products data samples to manipulate opinion unit mapping process and the result of this experiment is to find the accuracy rate 89% of matched opinion unit, the distance between “future related word” and opinion unit less than 8 words in most sentences, and reaching 60% corresponding to “future” definition. Using Graphic style describes user product opinions and product expectations as deducing to future related words in final conclusion of this research.
    Appears in Collections:[資訊管理學系暨研究所] 學位論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML50View/Open

    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