English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 56378/90242 (62%)
造访人次 : 11682521      在线人数 : 40
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: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/115252


    题名: Detecting Spamming Reviews Using Long Short-term Memory Recurrent Neural Network Framework
    作者: Wang, Chih-Chien;Day, Min-Yuh;Chen, Chien-Chang;Liou, Jia-Wei
    关键词: Fake Review;Deep Learning;Neural Network;Long Short-term Memory (LSTM);Recurrent Neural Network (RNN)
    日期: 2018-06-13
    上传时间: 2018-10-18 12:12:17 (UTC+8)
    摘要: Some unethical companies may hire workers (fake review spammers) to write reviews to influence consumers' purchasing decisions. However, it is not easy for consumers to distinguish real reviews posted by ordinary users or fake reviews post by fake review spammers. In this current study, we attempt to use Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) framework to detect spammers. In the current, we used a real case of fake review in Taiwan, and compared the analytical results of the current study with results of previous literature. We found that the LSTM method was more effective than Support Vector Machine (SVM) for detecting fake reviews. We concluded that deep learning could be use to detect fake reviews.
    關聯: Proceedings of the 2nd International Conference on E-commerce, E-Business and E-Government (ICEEG 2018)
    DOI: https://doi.org/10.1145/3234781.3234794
    显示于类别:[資訊管理學系暨研究所] 會議論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML62检视/开启
    index.html0KbHTML97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