AI and machine learning for detecting social media-based fraud targeting small businesses
1 Montclair State University, Montclair, New Jersey, USA.
2 CISCO, Nigeria.
3 Globacom Nigeria Limited.
4 Department of Computer Science, Texas Southern University, Texas, USA.
Review
Open Access Research Journal of Engineering and Technology, 2024, 07(02), 142-152.
Article DOI: 10.53022/oarjet.2024.7.2.0067
Publication history:
Received on 09 November 2024; revised on 22 December 2024; accepted on 24 December 2024
Abstract:
Social media has become an essential tool for small businesses in the digital age, offering unprecedented marketing and customer engagement opportunities. However, this widespread use also exposes these businesses to a growing threat of social media-based fraud. This review paper explores the role of Artificial Intelligence (AI) and machine learning in detecting and mitigating such fraud. It examines the common types of social media fraud targeting small businesses, the evolving tactics employed by fraudsters, and the challenges in detecting these fraudulent activities due to the dynamic nature of social media platforms. The paper delves into various AI and machine learning approaches for fraud detection, including the use of advanced algorithms, Natural Language Processing (NLP), and real-time anomaly detection. Furthermore, it discusses the integration of AI tools with social media platforms, highlighting the role of APIs, data privacy concerns, and the benefits of automation and continuous learning systems. Finally, the paper outlines future trends and provides recommendations for small businesses, emphasizing the importance of adopting AI-based solutions and the roles of policymakers and platform providers in supporting these technologies. By synthesizing current knowledge and offering actionable insights, this paper aims to enhance the understanding of AI-driven fraud detection in social media and provide guidance for small businesses seeking to safeguard their operations.
Keywords:
Social Media Fraud; AI Fraud Detection; Machine Learning; Natural Language Processing (NLP); Real-Time Anomaly Detection; Data Privacy
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0