Authors:
Ravishankar S. Ulle, S. Yogananthan

Addresses:
Department of Management Studies, CMS Business School, Jain University, Bangalore, Karnataka, India. dr.ravishanakrulle@cms.ac.in, dr.s_yogananthan@cms.ac.in

Abstract:

The proliferation of fake online opinions undermines consumer trust and distorts decision-making processes. Traditional detection methods relying on content analysis face limitations, such as difficulty in identifying sophisticated fraudulent behavior and adapting to new patterns. This paper investigates the potential of combining behavioral analysis with machine learning (ML) to improve the detection of fake reviews. Through a comprehensive review of existing literature, we explore behavioral analysis techniques for identifying suspicious activities and the application of ML algorithms for automated detection. We propose a conceptual framework focusing on reviewer behavior, review content, and review authenticity as primary variables while considering platform characteristics and product categories as moderating factors and reviewer motivation as a mediating factor. The integration of these dimensions aims to capture the nuances of fraudulent activities and enhance detection accuracy. By identifying key research gaps, such as the lack of real-time detection methods and insufficient focus on behavioral indicators, this review formulates targeted research questions to guide future studies. Our findings suggest that the synergy between behavioral analysis and ML holds promise for developing robust systems to unmask fake online opinions. This research contributes to advancing detection methods and restoring consumer trust in online platforms.

Keywords: Fake Online Opinions; Behavioral Analysis; Machine Learning (ML); Fraudulent Actors; Content Analysis; Sentiment Analysis; Reviewer Motivation; Support Vector Machine (SVM); Adaptive Boosting (AB).

Received on: 21/11/2023, Revised on: 25/01/2024, Accepted on: 11/03/2024, Published on: 03/06/2024

DOI: 10.69888/FTSML.2024.000235

FMDB Transactions on Sustainable Management Letters, 2024 Vol. 2 No. 2, Pages: 51-64

• Views : 171
• Downloads : 6

Download PDF