ABSTRACT :
Online marketplaces often witness opinion spam in the form of reviews. People are often hired to target specific brands for promoting or impeding them by writing highly positive or negative reviews. This often is done collectively in groups. Although some previous studies attempted to identify and analyze such opinion spam groups, little has been explored to spot those groups who target a brand as a whole, instead of just products. In this article, we collected the reviews from the Amazon product review site and manually labeled a set of 923 candidate reviewer groups. The groups are extracted using frequent itemset mining over brand similarities such that users are clustered together if they have mutually reviewed (products of) a lot of brands. We hypothesize that the nature of the reviewer groups is dependent on eight features specific to a (group, brand) pair. We develop a feature-based supervised model to classify candidate groups as extremist entities. We run multiple classifiers for the task of classifying a group based on the reviews written by the users of that group to determine whether the group shows signs of extremity. A three-layer perceptron-based classifier turns out to be the best classifier. We further study behaviors of such groups in detail to understand the dynamics of brand-level opinion fraud better. These behaviors include consistency in ratings, review sentiment, verified purchase, review dates, and helpful votes received on reviews. Surprisingly, we observe that there are a lot of verified reviewers showing extreme sentiment, which, on further investigation, leads to ways to circumvent the existing mechanisms in place to prevent unofficial incentives on Amazon.
EXISTING SYSTEM :
There have been extensive studies on mining online reviews and classifying them based on user sentiment [8]–[11]. Reviews have also been extensively used in developing and augmenting recommendation systems [12]–[15] and extracting product features [16]–[18]. Another study has also shown the utility of product reviews in explaining the recommendations given by a recommendation system [19]. Pang et al. [20] showed the progression of reviews as an important part of the decision-making process with the advent of Web 2.0 and studied them from retrieval perspective. Since it is difficult for the buyer to wade through volumes of reviews, researchers have conducted studies on summarizing reviews based on user sentiment [21] and other features [22]–[24] as well under the umbrella of opinion summarization. All these studies indicated that product reviews are an invaluable resource for determining the quality of a product. Various marketing studies have also shown that reviews play an important role in maintaining the online reputation of a brand as well.
PROPOSED SYSTEM :
no data set of consumer reviews (on Amazon) that consists of brand information exists so far. Thus, we attempted to create the first data set of its kind by crawling reviews from Amazon.in, the Indian counterpart of the e-commerce giant. In this data set, along with the regular metadata, we also obtained the brand on which a review was posted. Other metadata per-review include reviewer id, product id (ASIN), brand, rating, review text, date, and the number of helpful votes a review has received.
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
