Unfair Reviews Detection on Amazon Reviews using Sentiment Analysis with Supervised Learning Techniques

Abstract

Reputation and trust are significantly important and play a pivotal role in enabling multiple parties to establish relationships that achieve mutual benefit especially in an E-Commerce (EC) environment. There are several factors negatively affecting the sight of customers and sellers in terms of reputation. For instance, lack of credibility in providing feedback reviews, by which users might create phantom feedback reviews to support their reputation. Thus, we will feel that these reviews and ratings are unfair. In this study, we have used Sentiment Analysis (SA) which is now the subject generating the most interest in the field of text analysis. One of the major challenges confronting SA today is how to detect unfair negative reviews, unfair neutral reviews and unfair positive reviews from opinion reviews. Sentiment classification techniques are used against a dataset of consumer reviews. Precisely, we provide comparison of four supervised machine learning algorithms: Naïve Bayes (NB), Decision Tree (DT-J48), Logistic Regression (LR) and Support Vector Machine (SVM) for sentiment classification using three datasets of reviews, including Clothing, Shoes and Jewelry reviews, Baby reviews as well as Pet Supplies reviews. In order to evaluate the performance of sentiment classification, this work has implemented accuracy, precision and recall as a performance measure. Our experiments' results show that the Logistic Regression (LR) algorithm is the best classifier with the highest accuracy as compared to the other three classifiers, not merely in text classification, but in unfair reviews detection as well.

The importance of behavioral data to identify online fake reviews for tourism businesses: a systematic review

“…Some works (Lin et al, 2014;Zhang et al, 2016;Ramalingam & Chinnaiah, 2018) were included as part of the analysis because their results can be implemented in every industry that allows consumers to write reviews, including the tourism industry. Elmurngi & Gherbi (2018) analyzed false reviews in E-commerce, considering that TripAdvisor is the most important e-commerce platform in the hospitality industry; therefore, this study might be of interest to the present study (Reyes-Menendez, .…”

“…As demonstrated in the present review, different methods have been used in previous research on false reviews. These include the development of algorithms based on Big Data from the social platforms themselves (e.g., Chang et al, 2015;Li et al, 2014) as well as sentiment analysis of written comments (Chen, Guo & Deng, 2014;Elmurngi & Gherbi, 2018). Finally, there is a group of studies that used other methodological approaches (Hunt, 2015;Ramalingam & Chinnaiah, 2018).…”

SAFER: Sentiment Analysis-Based FakE Review Detection in E-Commerce Using Deep Learning

“…Elshrif et al [3], in their work, provide a comparison of four supervised machine-learning algorithms: Naive Bayes (NB), Decision Tree (DT-J48), Logistic Regression (LR), and SVM for sentiment classification using three e-commerce "Amazon" sample datasets. The dataset includes reviews of clothes, shoes, and jewels.…”

“…With the increasing importance of online reviews, the tendency to manipulate customers by posting fake/false reviews has also increased drastically. Many organizations use fake reviews as a tool to boost their product sales, and many use them to drop the value of other organizations [3,4]. These reviews are posted by either a single spammer or a group of spammers hired by an organization/company to manipulate customers.…”

A Study on Opinion Spamming: Fake Consumer Review Detection

“…In a new report, a technique was proposed by E.I Elmurngi and A. Gherbi [1] utilizing an open-source programming apparatus called 'Weka instrument' to actualize AI calculations utilizing assessment examination to arrange reasonable and unreasonable surveys from amazon audits dependent on three unique classifications positive, negative and unbiased words. In this exploration work, the spam audits are distinguished by just including the supportiveness votes casted a ballot by the clients alongside the rating deviation are viewed as which restricts the general exhibition of the framework.…”