English  |  正體中文  |  简体中文  |  Items with full text/Total items : 67621/67621 (100%)
Visitors : 23044048      Online Users : 297
RC Version 7.0 © 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
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/59981

    Title: 辨別含有可疑內容網路產品評論之研究;Identify the online product comments with suspicious content
    Authors: 雷秉翰;Lei,Ping-han
    Contributors: 企業管理學系
    Keywords: 網路口碑;文字探勘;謠言;網路謠言;模糊性詞語;網路產品評論;Electronic Word-of-mouth (eWOM);Text mining;Rumors;Fuzzy words
    Date: 2013-06-25
    Issue Date: 2013-07-10 11:53:55 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 在現今這個網路發達的時代,「網路口碑」比起傳統的口碑行銷更具影響力, 企業必須重視顧客之間經驗交流及「網路口碑」所帶來的影響。「網路口碑」可 為企業帶來正面和負面的效果,顧客在網路上發表使用過產品的心得,讓潛在消 費者能夠更了解產品特性,產品討論度提高也為企業帶來知名度
    關於產品的流 言或負面謠言也可能在網路上流傳,虛假不實或誇大的內容對產品和企業商譽都 可能帶來重大傷害。
    本研究以謠言作為研究核心,探討謠言的組成要件及網路謠言的影響層面, 以智慧型手機之網路謠言作為分析對象,將謠言組成要件分為兩項:產品之重要 屬性以及文章中模糊性詞彙數量。根據謠言相關研究及漢語詞性的研究分類,發 展出分類漢語謠言文章的模型與詞庫,並運用文字探勘技術,對網路產品評論文 章進行分析與比對,建立出一套可自動分類出謠言文章的方法。
    本研究所發展出的模型結果發現,含有產品之重要屬性詞彙以及模糊性詞彙 愈多且總字數愈少的文章,其內容為謠言的可能性越高,研究結果也顯示模型可 有效區隔出謠言與正常反應問題之文章,使用本研究收集之訓練資料其效果為精 確度(Precision)=71.43%,召回率(Recall)=73.5%,F-measure=72.45%
    測試資料之效果為精確度(Precision)=80%,召回率(Recall)=73.73%,F-measure =76.19%。
    Internet is the most rapidly growing communication medium for marketing. Not only the companies could promote their latest product online, but also the consumers could make comments and product reviews. The online reviews written by the consumers are more persuasive than the advertisement or official statement because of its objectivity. If there are some product defects, the information could be founded in online product reviews written by different people. On the other hand, well-designed products could be highly thought of and praised by their customers. Recently, people who need more information about the goods they planned to purchase will look for the online product reviews before the purchasing. This is how “Electronic Word-of-mouth” (eWOM) influences or even changes the purchasing decision.
    The purpose of this research is to identify the worst kind of the online product reviews: rumors. Rumors could cause serious damage to company’s goodwill and the sale of the product. In this study, we developed a new method that combined the research of rumors and the text mining techniques. Breaking the content of online product review into two components, and then use the “Keyword matching” technique to evaluate whether it is a rumor article. The result of this method shows that it could precisely identify those rumor articles from bunch of online product reviews. We could use it as a filter when we search for product information and make a better and more suitable buying decision.
    Appears in Collections:[企業管理研究所] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明