Classification Model of Online Review Credibility on E-commerce Platform

DOI

10.2991/iccessh-19.2019.353How to use a DOI?

Keywords

online review; credibility; logistic regression; sentiment analysis

Abstract

With the increasing popularity of e-commerce, the phenomenon of network ghostwriters brushing praise, merchants deliberately denigrating competitors, and users using comment templates to cope with the comment task is emerging in an endless stream. Starting from the credibility of online reviews, this paper studies the data characteristics of fake reviews, and constructs a logistic regression model from the four dimensions of the length of reviews, the similarity of reviews, the difference between the text emotional tendency and actual score, and the number of days between the confirming receipt and the release of comments, so as to classify the online reviews' credibility. The validity of the method is verified by using the review set of iPhone on Jingdong platform.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zimo Li
PY  - 2019/07
DA  - 2019/07
TI  - Classification Model of Online Review Credibility on E-commerce Platform
BT  - Proceedings of the 4th International Conference on Contemporary Education, Social Sciences and Humanities (ICCESSH 2019)
PB  - Atlantis Press
SP  - 1635
EP  - 1640
SN  - 2352-5398
UR  - https://doi.org/10.2991/iccessh-19.2019.353
DO  - 10.2991/iccessh-19.2019.353
ID  - Li2019/07
ER  -