Volume 18, No. 4, 2021
Detecting Fake Reviews Through Multinomial Naive Bayes Algorithm With Deep Learning Techniques
Mr.Senthil S.Sekhar , Dr.K.Satyanarayana
Abstract
Nowadays online data generation and consumption plays an important role in the field of information technology. Customer has to purchase any product through online needs the past history and review result for achieving better reliability. Traditionally various kind of recommendation systems are available with single source and specific form of review. The impact of online reviews on businesses has grown dramatically over the past years, it is important to determine business success in a variety of sectors, from restaurants, hotels to e- commerce. Unfortunately, some users use illegal means to improve their online reputation by writing fake reviews for their businesses or competitors. Previous studies have focused on the detection of fraud in many domains, such as product or business reviews in restaurants and hotels. However, despite its economic interest, the background of the electronic consumer business has not been well-studied. This article proposes a theoretical framework for detecting false reviews that have been explored in the consumer retail domain. The contributions are threefold: 1. Definition of a feature framework for fake review detection, 2. Development of a fake review classification method based on the proposed framework, 3. Evaluation and analysis of the results for each of the site under study.
Pages: 86-96
Keywords: e-commerce, fake review, reliability, recommendation