| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 6873028 | Future Generation Computer Systems | 2018 | 7 Pages |
Abstract
The purpose of this paper is to explore a method for detecting abnormal comments. With the growth of e-commerce sites and reviews sites, user reviews of messages begin to affect merchant's revenue and impact consumer's choice. It is meaningful to help users get real comment messages by using natural language processing means. In this paper, the doc2vec model, the clustering algorithm and emotion analysis are applied to identify abnormal comments.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
Wenbing Chang, Zhenzhong Xu, Shenghan Zhou, Wen Cao,