Enactment of Ensemble Learning for Review Spam Detection on Selected Features

DOI

10.2991/ijcis.2019.125905655How to use a DOI?

Keywords

Review spam; Ensemble learning module; Positive polarity; Negative polarity

Abstract

In the ongoing era of flourishing e-commerce, people prefer online purchasing products and services to save time. These online purchase decisions are mostly influenced by the reviews/opinions of others who already have experienced them. Malicious users use this experience sharing to promote or degrade products/services for their iniquitous monetary benefits, known as review spam. This study aims to evaluate the performance of ensemble learning on review spam detection with selected features extracted from real and semi-real-life datasets. We study various performance metrics including Precision, Recall, F-Measure, and Receiver Operating Characteristic (RoC). Our proposed ensemble learning module (ELM) with ChiSquared feature selection technique outperformed all others with 0.851 Precision.

Copyright

© 2019 The Authors. Published by Atlantis Press SARL.

Open Access

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

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Faisal Khurshid
AU  - Yan Zhu
AU  - Zhuang Xu
AU  - Mushtaq Ahmad
AU  - Muqeet Ahmad
PY  - 2019
DA  - 2019/01/28
TI  - Enactment of Ensemble Learning for Review Spam Detection on Selected Features
JO  - International Journal of Computational Intelligence Systems
SP  - 387
EP  - 394
VL  - 12
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.2019.125905655
DO  - 10.2991/ijcis.2019.125905655
ID  - Khurshid2019
ER  -