Detecting Spamming Reviews Using Long Short-term Memory Recurrent Neural Network Framework

淡江大學機構典藏 > 商管學院 > 資訊管理學系暨研究所 > 會議論文 > Item 987654321/115252

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/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:	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.html		0Kb	HTML	176	检视/开启
index.html		0Kb	HTML	275	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