期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于隐含语义分析的电商虚假评论识别

Identification of Fake Online Products' Reviews based on Latent Semantic Analysis
下载PDF
导出
摘要 针对目前虚假评论识别都是通过评论者或评论文本的显式特征来进行的,但是没有考虑评论文本的语义信息,分析结果不够准确,因此提出基于隐含语义分析的电商虚假评论识别方法.该方法在基于用户行为特征分析的基础上增加了评论文本的语义分析信息,能在文本语义层次上识别虚假评论,提升了识别准确性.方法中给出了评论文本的可信度度量并针对有序的可信度度量提出了一种新的错位级别评估方法. Aiming at fake reviews recognition is carried out through the explicit characteristics of critics or review texts,but did not consider the semantic information of text comments,the results are not accurate enough,so put forward the latent semantic analysis of fake reviews recognition method based on electricity supplier comments.Based on the analysis of user behavior characteristics,this method increases the semantic analysis information of the comment text,which makes it possible to identify the fake reviews on the semantic level of the text and improve the recognition accuracy.We propose a new method level of dislocation to evaluate the reliability of the comment text.
作者 李存林 杨世瀚 王晗 LI Cun-lin;YANG Shi-han;WANG Han(Guangxi Key Laboratory Guangxi of Hybrid Computation and IC Design Analysis for Nationalities, Nanning 530006, Chin)
机构地区 广西民族大学广西混杂计算与集成电路设计分析重点实验室
出处 《广西民族大学学报（自然科学版）》 CAS 2018年第1期52-59,共8页 Journal of Guangxi Minzu University ：Natural Science Edition
基金 国家自然科学基金(11371003 11461006) 广西科技基地和人才专项(2016AD05050) 广西"八桂学者"专项 广西自然科学基金(2014GXNSFAA118359)
关键词 商品评论 隐含语义分析 虚假评论识别 错位级别 Commodity reviews Latent semantic analysis Identification of fake reviews Level of dislocation
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献1

二级参考文献11

  • 1Jindal N, Liu B. Review spam detection [ C ]//Proceed- ings of the 16th international conference on World Wide Web. 2007 : 1189-1190.
  • 2Luca M, Zervas G. Fake It Till You Make It: Reputa- tion, Competition, and Yelp Review Fraud[ Z]. Harvard Business School Working Paper. 2013:14-006.
  • 3Wang G, Xie S, Liu B, et al. Review graph based online store review spammer detection [ C ]//IEEE 11 th Interna- tional Conference on Data Mining. 2011: 1242-1247.
  • 4Lim E P, Nguyen V A, Jindal N, et al. Detecting prod- uct review spammers using rating behaviors [ C ]//Pro- ceedings of the 19th ACM international conference on In- formation and knowledge management. 2010: 939-948.
  • 5Xie S, Wang G, Lin S, et al. Review spam detection via temporal pattern discovery [ C ]//Proceedings of the 18th ACM SIGKDD international conference on Knowledge dis- covery and data mining. 2012: 823-831.
  • 6Wu G, Greene D, Cunningham P. Merging multiple cri- teria to identify suspicious reviews [ C ]//Proceedings of the fourth ACM conference on Recommender systems. 2010:241-244.
  • 7Hern6ndez D, Guzm6n R, M6ntes y Gomez M, et al. U- sing PU-learning to detect deceptive opinion spare [ C ]// Proceedings of the 4th Workshop on Computational Ap- proaches to Subjectivity, Sentiment and Social Media A- nalysis. 2013 : 38-45.
  • 8Liu B, Lee W S, Yu P S, et al. Partially supervised classification of text documents [ C ]//Proceedings of the 19th international conference on Machine learning. 2002:387-394.
  • 9Liu B, Dai Y, Li X, et al. Building text classifiers using positive and unlabeled examples [ C ]//Third IEEE Inter- national Conference on Data Mining. 2003: 179-186.
  • 10Li H, Chen Z, Liu B, et al. Spotting Fake Reviews via Collective Positive-Unlabeled Learning[ C ]//IEEE 14th International Conference on Data Mining. 2014: 899 -904.

共引文献2

广西民族大学学报（自然科学版）
2018年 第1期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部