Reputation Reporting System using Text Based Classification
Divyanshu Jalther1, Priya G2

1Divyanshu Jalther, School of Computer Science and Engineering (SCOPE), VIT University, Vellore, (Tamil Nadu), India.
2Priya G, School of Computer Science and Engineering (SCOPE), VIT University, Vellore, (Tamil Nadu), India.

Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 1555-1558 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7100068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Reputation System is a system which allow users to rate and review an organization or a product so that other users or customers can judge an organization, or a product be seeing the reviews and ratings of an organization or a product. But the predictive value of reputation reporting system can be manipulated either by buyers or competitors to promote or demote a product or an organization. Fake review detection has attracted significant research attention in recent years. Some research has been done using dataset produced by fake review generator which was found inefficient. Some research has been done using behavioral pattern of spammers and pattern of fake reviews written which has produced some better results. In this paper, we implemented an approach to detect biased feedback using supervised machine learning algorithm. We used data from which contains labelled dataset of restaurants in New York to train and test different classifier. In the end, we compared the accuracy of different classifiers to conclude which classifier has worked best on textual data. This model can be used by any service or product provider companies to detect and deleted biased feedback from their website.
Keyword: Machine Learning, Reputation System, Text based Classification, Online Fraud.
Scope of the Article: Classification.