AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We have introduced three automated approaches to deceptive opinion spam detection, based on insights coming from research in computational linguistics and psychology

Finding deceptive opinion spam by any stretch of the imagination

meeting of the association for computational linguistics, (2011): 309-319

引用1427|浏览312
EI
下载 PDF 全文
引用
微博一下

摘要

Consumers increasingly rate, review and research products online (Jansen, 2010; Litvin et al., 2008). Consequently, websites containing consumer reviews are becoming targets of opinion spam. While recent work has focused primarily on manually identifiable instances of opinion spam, in this work we study deceptive opinion spam---fictitious...更多

代码

数据

基金
  • Indeed, a two-tailed binomial test fails to reject the null hypothesis that JUDGE 2 and JUDGE 3 perform at-chance (p = 0.003, 0.10, 0.48 for the three judges, respectively)
  • The psycholinguistic approach (LIWCSVM) proposed in Section 4.2 performs 3.8% more accurately (one-tailed sign test p = 0.02), and the standard text categorization approach proposed in Section 4.3 performs between 14.6% and 16.6% more accurately
0
您的评分 :

暂无评分

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn