English  |  正體中文  |  简体中文  |  Items with full text/Total items : 51258/86283 (59%)
Visitors : 8019852      Online Users : 66
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/987654321/112054


    Title: Exploring Review Spammers by Review Similarity: A Case of Fake Review in Taiwan
    Authors: Min-Yuh Day, Chih-Chien Wang, Chien-Chang Chen, Shao-Chieh Yang
    Keywords: Spam, Fake reviews, Text mining, Cosine similarity
    Date: 2017-07-31
    Issue Date: 2017-11-14 02:10:25 (UTC+8)
    Abstract: Understanding the phenomenon of spam reviews in social media is now an emerging and important issue since some enterprises may hire spammers to post fake reviews to promote their product or demote product of their competitors. The hired spammers are paid based on the fake reviews. Thus, these spammers may rewrite previous reviews as new review to earn the money. Thus, review similarity maybe a cue to detect fake reviews. Although literature had investigated the spam reviews, the review similarity of real review spammers is relatively unexplored. The objective of this paper is to explore the review spammers with a real case of fake reviews in Taiwan by investigating the cosine similarity and content length of reviews. We have proposed a text mining approach for a better understanding the phenomenon of fake reviews. The empirical results suggested that when comparing with normal reviews, the spam reviews were longer and with higher content similarity.
    Relation: The Third International Conference on Electronics and Software Science (ICESS 2017)
    Appears in Collections:[資訊工程學系暨研究所] 會議論文

    Files in This Item:

    There are no files associated with this item.

    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