Fake Reviews Detection through Ensemble Learning

Abstract

Customers represent their satisfactions of consuming products by sharing their experiences through the utilization of online reviews. Several machine learning-based approaches can automatically detect deceptive and fake reviews. Recently, there have been studies reporting the performance of ensemble learning-based approaches in comparison to conventional machine learning techniques. Motivated by the recent trends in ensemble learning, this paper evaluates the performance of ensemble learningbased approaches to identify bogus online information. The application of a number of ensemble learning-based approaches to a collection of fake restaurant reviews that we developed show that these ensemble learning-based approaches detect deceptive information better than conventional machine learning algorithms.

Multi-task Ensemble Learning for Fake Reviews Detection and Helpfulness Prediction: A Novel Approach

“…Several studies employ machine learning methodologies such as Support Vector Machines (SVM) (Ott et al, 2011;Mukherjee et al, 2012;Yafeng et al, 2014;Melleng et al, 2019;Wang et al, 2014), Random Forest (Rout et al, 2017Gutierrez-Espinoza et al, 2020), Naive Bayes (Li et al, 2011), Logistic Regression (Banerjee et al, 2015), and Decision Trees (Gutierrez-Espinoza et al, 2020). On the other hand, some research explores the utility of Deep Learning techniques.…”