Deep Learning-Based Approach for Monitoring and Controlling Fake Reviews

Nilesh  Sable; Parikshit   Mahalle; Kalyani  Kadam; Bipin  Sule; Rahul Joshi; Mahendra Deore

doi:10.47852/bonviewJCCE42023602

Authors

Nilesh Sable Department of Computer Science and Engineering, BRACT's Vishwakarma Institute of Technology, India
Parikshit Mahalle Department of Artificial Intelligence and Data Science, BRACT's Vishwakarma Institute of Technology, India https://orcid.org/0000-0001-5474-6826
Kalyani Kadam Department of Artificial Intelligence and Machine Learning, Symbiosis Institute of Technology, India https://orcid.org/0000-0002-3481-2811
Bipin Sule Department of Engineering, Sciences and Humanities, BRACT's Vishwakarma Institute of Technology, India
Rahul Joshi Department of Computer Science and Engineering, Symbiosis Institute of Technology, India https://orcid.org/0000-0002-5871-890X
Mahendra Deore Department of Computer Engineering, MKSSS’S Cummins College of Engineering for Women, India https://orcid.org/0000-0002-8499-7797

DOI:

https://doi.org/10.47852/bonviewJCCE42023602

Keywords:

E-commerce, recurrent neural network (RNN), authorship, suspicion, spam indicators

Abstract

In the last decade, E-commerce has developed into the world's biggest stage for shopping. It has allowed people around the world to directly communicate without any barriers to purchasing the products as per requirements. Internet technologies have reshaped E-commerce since product reviews have become a vital part of online shopping due to their rapid growth. But with widespread usage, it has also brought forth an influx in rates of fake reviews. Fake reviews, which are frequently used to influence public perception, are now a widespread occurrence due to the open nature of E-commerce. Using different learning techniques, many methods and techniques are implemented to spot false reviews and fake behavior. This research aims to use a recurrent neural network (RNN) to combine content and data to identify false product reviews. The proposed approach, which is related to spam indicators, makes use of both product reviews and reviewers' behavioral characteristics. The fine-grained burst pattern analysis is used to conduct a more thorough investigation of produced testimonials during "suspicious" periods in the proposed approach. Additionally, a customer's previous review data are utilized to determine their overall "authorship" reputation, which serves as a barometer for the authenticity of most recent reviews. For the proposed theory, we examined the real-world Amazon review dataset and produced more accurate findings than previous methodologies. In addition to this, our proposed deep learning-based model performance has been validated utilizing the benchmark Yelp Open dataset and IMDB dataset.

Received: 12 June 2024 | Revised: 29 July 2024 | Accepted: 18 August 2024

Conflict of Interest

The authors declare that they have no conflicts of interest in this work.

Data Availability Statement

Data available on request from the corresponding author upon reasonable request.

Author Contribution Statement

Nilesh Sable: Conceptualization, Methodology, Software, Validation, Data curation, Writing – original draft, Writing – review & editing. Parikshit Mahalle: Conceptualization, Software, Resources, Supervision. Kalyani Kadam: Formal analysis, Writing – review & editing, Visualization. Bipin Sule: Methodology, Writing – original draft. Rahul Joshi: Investigation, Visualization. Mahendra Deore: Software, Validation, Writing – original draft, Writing – review & editing.