Submit Your Manuscript Online

Fake Review Spammer Groups Detection From Product Reviews

	International Journal of Scientific Research and Engineering Development (IJSRED)	Full Text:
	Published Issue : Volume-3 Issue-6
	Year of Publication : 2020
	Unique Identification Number : IJSRED-V3I6P27
	Authors : R.Sudhakar
	: Click Here

Abstract :

Presently, online product reviews play a Important role in the purchase decision of consumers. A high amount of positive reviews will bring extensive sales development, while negative reviews will cause sales loss. So many spammers try to promote their products or demote their competitors’ products by posting negative and partial online reviews. By registering a number of accounts, many individual spammers could be structured as spammer groups to manipulate the product reviews together and can be more critical.. In this paper, I propose a partially supervised learning model (PSGD) to detect spammer groups. Through classification some spammer groups as positive instances, PSGD applies positive unlabeled learning (PU-Learning) to study a classified as spammer group detector from positive instances (labelled spammer groups) and unlabeled instances (unlabeled groups).I extract consistent negative set in terms of the positive instances and the distinctive features. By combining the positive instances, extracted negative instances and unlabeled instances, Ichange the PU-Learning problem into the famous semi supervised learning problem, and then use a Naive Bayesian model and an EM algorithm to train a classifier for spammer group detection.